Design World Robotics Handbook 11 2023

www.designworldonline.
com
November 2023
2023
ROBOTICS
HANDBOOK
We came. We saw.
We automated.
Our storing, conveying and picking robots
and solutions make automating your
warehouse simpler and quicker than ever.
movu-robotics.com
Servo Gearheads
for AMR/AGV Propulsion
HPG Gearheads
The Harmonic Gearhead® gearbox design allows for backdrivability while ensuring high-
efficiency performance, maximizing elapsed operational time before recharging is necessary.
High-capacity cross roller bearing supports heavy payloads.
High Efficiency Easy Mounting to a Wide Variety

Up to 95% Efficiency of Servomotors
Quick Connect® motor adaptation system includes
Low Backlash for Life a clamshell style servo coupling and piloted adapter
Innovative ring gear inherently compensates for flange.
interference between meshing parts, ensuring
consistent, low backlash for the life of the gearhead. Flange Output Standard
Flanged output is standard for convenient, stable
High Load Capacity Output Bearing wheel mounting.
A Cross-Roller bearing is integrated with the output
flange to provide high moment stiffness, high load
capacity and precise positioning accuracy.
Harmonic Drive LLC | 42 Dunham Ridge | Beverly, MA 01915 | 800.921.3332 | www.HarmonicDrive.net

Harmonic Drive®, Harmonic Planetary®, Harmonic Gearhead® and Quick Connect® are registered trademarks of Harmonic Drive LLC.
DW 9x10.875 HPG Ad.indd 1 10/25/23 10:14 AM

Contents
ON THE COVER
Inside the development of
11 • 2023 therobotreport.com
Apptronik’s Apollo humanoid

PAGE 14
COLLABORATIVE ROBOTICS SENSORS

08 32
Welding cobot delivers 10x production 3D cameras enable automatic loading
boost for marine exhaust manufacturer of pressed parts
DeAngelo Marine Exhaust has increased Four 3D cameras from IDS Imaging each
weld speed, lowered lead times, and record a part of the entire image field,
improved quality using its new cobot resulting in data from multiple perspectives
colleague. for a higher quality 3D point cloud.
DESIGN & DEVELOPMENT

38
How computer vision increases
productivity & sustainability in
agriculture
14
Inside the development of Apptronik’s
Integrating computer vision and other
Apollo humanoid
advanced technologies like sensors,
The company’s R&D work on exoskeletons
robotics, and AI will result in more efficient
and bipedal locomotion for the U.S.
and more automated machines that can
government and Department of Defense has
treat every single plant at a micro level.
it primed for the humanoid era.
40
Commercializing tactile sensors for
24
Teaching robots new tricks with robot dexterity
Generative AI Addressing practical issues such as
Researchers are exploring how large usefulness, reliability and affordability.
language models can be applied to robotics
design, model training, simulation, control
algorithms and more. SOFTWARE
30 44
Humanoids getting their feet wet in Bridging the gap between research,
logistics industrial robotics using ROS
Humanoids offer the potential flexibility Tormach created a ROS-based industrial
and scalability to be used within existing robotic manipulator and control system
warehouses alongside humans to help pick, that avoids “black box” issues that can
move and sort goods. plague modern robotics applications.
2 November 2023 www.therobotreport.com THE ROBOT REPORT

231002_CJCI_DW_US.indd 1 10/2/23 5:05 PM
ALL IN
AI-based code reading is just minutes away.
LEARN MORE
Lector One Box is a registered trademark of SICK Sensor Intelligence WWW.SICK.COM

The new generation of RENCO rotary encoders
Motor commutation at the push of a button
Are you looking for a rotary encoder that is easy to install signals. Afterwards, rest assured in dependable operation
and reliable to operate? Then meet the new R35i and R35iL thanks to features for monitoring and diagnostics never
models from RENCO. Once you’ve used their built-in before implemented in an incremental rotary encoder.
mounting aid for fast and easy installation, simply push a That’s what makes these encoders the ideal motor feed-
button to electronically adjust the motor commutation back solutions for stepper and BLDC motors.
ders
Enco ery
v
for e or HEIDENHAIN CORPORATION
mot sps.heidenhain.com www.heidenhain.us
DESIGN WORLD
Follow the whole team @DesignWorld
EVENTS
EDITORIAL Director, Audience
Development Events Manager
VP, Editorial Director Bruce Sprague Jen Osborne
Paul J. Heney bsprague@wtwhmedia.com josborne@wtwhmedia.com
pheney@wtwhmedia.com @wtwh_jen
@wtwh_paulheney WEB DEV / DIGITAL
OPERATIONS Events Manager
Managing Editor Brittany Belko
Mike Santora Web Development Manager
bbelko@wtwhmedia.com
msantora@wtwhmedia.com B. David Miyares
DESIGN
@dw_mikesantora dmiyares@wtwhmedia.com
Event Marketing Specialist
@wtwh_webdave
Olivia Zemanek
Executive Editor ozemanek@wtwhmedia.com
Lisa Eitel Senior Digital Media
leitel@wtwhmedia.com Manager VIDEO SERVICES
GUIDES
@dw_lisaeitel Patrick Curran
pcurran@wtwhmedia.com Videographer
Senior Editor @wtwhseopatrick Garrett McCafferty
Miles Budimir gmccafferty@wtwhmedia.com
mbudimir@wtwhmedia.com Front End Developer
@dw_motion Melissa Annand Videographer
mannand@wtwhmedia.com Kara Singleton
Brought to you by Senior Editor ksingleton@wtwhmedia.com
Mary Gannon Software Engineer
mgannon@wtwhmedia.com David Bozentka PRODUCTION SERVICES
@dw_marygannon dbozentka@wtwhmedia.com
Customer Service Manager
Senior Editor DIGITAL MARKETING
Stephanie Hulett
Rachael Pasini shulett@wtwhmedia.com
rpasini@wtwhmedia.com VP, Digital Marketing
@WTWH_Rachael Virginia Goulding
Key technology content vgoulding@wtwhmedia.com
Customer Service
Representative
produced by the editors Associate Editor
Heather Hall
@wtwh_virginia Tracy Powers
tpowers@wtwhmedia.com
of Design World. hhall@wtwhmedia.com Digital Marketing Manager
@wtwh_heathhall Taylor Meade Customer Service
tmeade@wtwhmedia.com Representative
Available for FREE download @WTWH_Taylor JoAnn Martin
CREATIVE SERVICES jmartin@wtwhmedia.com
in individual PDFs. Digital Marketing Coordinator
Meagan Konvalin Customer Service
VP, Creative Director
mkonvalin@wtwhmedia.com Representative
Matthew Claney
mclaney@wtwhmedia.com Renee Massey-Linston
Find these technical design @wtwh_designer
Digital Marketing Coordinator
Francesca Barrett
renee@wtwhmedia.com
guides on the Design World Art Director

fbarrett@wtwhmedia.com Customer Service
Representative
Design Guide Digital Library: Allison Washko
awashko@wtwhmedia.com
Webinar Coordinator Trinidy Longgood
Emira Wininger tlonggood@wtwhmedia.com
www.designworldonline.com/ Senior Graphic Designer
ewininger@wtwhmedia.com
design-guide-library Mariel Evans

mevans@wtwhmedia.com
Webinar Coordinator Digital Production Manager
Dan Santarelli Reggie Hall
@wtwh_mariel rhall@wtwhmedia.com
dsantarelli@wtwhmedia.com
Graphic Designer Digital Production Specialist
Shannon Pipik FINANCE Nicole Johnson
spipik@wtwhmedia.com njohnson@wtwhmedia.com
@wtwh_shannon Controller
Brian Korsberg Digital Design Manager
bkorsberg@wtwhmedia.com Samantha King
sking@wtwhmedia.com
Accounts Receivable Specialist
Jamila Milton Marketing Graphic Designer
EDITORIAL
jmilton@wtwhmedia.com
Hannah Bragg
Executive Editor Editor hbragg@wtwhmedia.com
Steve Crowe Mike Oitzman WTWH Media, LLC
scrowe@wtwhmedia.com moitzman@wtwhmedia.com TOP Digital Production Specialist
1111 Superior Ave. WORK
@SteveCrowe @MikeOitzman 26th Floor
PLACES
2022
Elise Ondak
2011 - 2020 2013 - 2017, 2021
eondak@wtwhmedia.com
Cleveland, OH 44114
Editorial Director Associate Editor Ph: 888.543.2447
Eugene Demaitre Brianna Wessling HUMAN RESOURCES
edemaitre@wtwhmedia.com bwessling@wtwhmedia.com
2014 - 2016
@GeneD5 Vice President of Human Resources
Medical Design Edith Tarter
& OUTSOURCING etarter@wtwhmedia.com

All products available directly on
RULAND.COM
WHAT’S NEW RULAND
TOOL-LESS ADJUSTMENT COMPONENTS
• Adjustable handles and knobs replace standard hardware
and can be used to torque components without tools.
• Levers can be used with Ruland shaft collars for quick
installation and adjustment.
Ruland Manufacturing is proud to

support the FIRST Robotics Competition
as a Gold Supplier of precision
shaft collars & couplings.
PRECISION COUPLINGS
• Beam couplings accommodate light weights and high
misalignment.
from
• Zero-backlash jaw couplings for vibration dampening

and a variety of performance options.
• Bellows couplings for high size to torque ratio.
MODULAR MOUNTING
SYSTEMS
• Assorted components allow you
to build small assemblies for
mounting sensors, conveyor rails,
SHAFT COLLARS machine guards, and more.
• Thousands of size and style options. • Optional pre-designed kits make
• Proprietary manufacturing processes it easier to select the right
ensure superior fit and finish. system for your application.
• 8 material options.
VIBRATION ISOLATING COMPONENTS QUICK CLAMPING COLLARS

• Rubber bumpers are ideal as end • No tools required to install,
stops or mounting feet. remove, and adjust.
• Vibration isolation mounts can • Best suited for systems
be sandwiched between that require frequent
components to dampen shock adjustments.
loads.
• Both types can have studs or
tapped holes.
ruland.com | sales@ruland.com
Collaborative Robotics DeAngelo Marine Exhaust
had nearly given up
automating complex,
manual TIG welds until
the company came across
Hirebotics’ Cobot Welder
that uses a UR10e cobot
arm equipped with a
welding torch.
| Universal Robots
Welding cobot delivers

10X PRODUCTION BOOST
for marine exhaust manufacturer
DeAngelo Marine Exhaust
has increased weld speed,
DeAngelo Marine Exhaust had nearly
given up automating
complex, manual TIG welds until the
for aircra quality welds on marine
engine exhaust parts. But the demand for
DeAngelo’s exhaust parts exceeded the
lowered lead times, and company came across Hirebotics’ Cobot capacity of the company’s labor-intensive
Welder. The Florida manufacturer of production. And CEO Justin Montes had no
improved quality using its exhaust parts has now been able to luck hiring more manual welders.
new cobot colleague. increase weld speed tenfold, lower lead
times, and improve quality using its
“What we do here is custom fabrication
at the highest level,” he said. “You’re not
new cobot colleague, which also helped going to pull in a welder off the street
STEVE CROWE DeAngelo break into new markets. and have him fabricating these systems.”
EXECUTIVE EDITOR
65 days. That’s how far behind That le the CEO to face his own worst
DeAngelo Marine Exhaust was on lead nightmare: letting down the finest boat
ROBOTICS
times at its worst point. Based in the heart builders, naval architects and engine
of ‘the yachting capital of the world’ in Fort companies in the world by delivering
Lauderdale, FL, DeAngelo is a synonym too late.

“That’s how I lose the account and never get it
back,” Montes explained. “We were at an impasse,
experiencing significant growing pains, and knew
we simply had to scale up; lower our lead times,
lower our price, and increase our capacity.”
Montes had heard about ‘these cobots’ coming
out and said, “It seemed like a good idea. So, we
started sending out parts to seven of the big
robotic welding companies to see if they could do
a demo weld.”
The results were underwhelming. A box of
returned demo parts shows products with holes
in the weld seam and irregular globs of molten
metal. “They were all struggling to match our
quality. When I contacted Universal Robots (UR),
I was already three months into this and had
almost given up,” Montes said.
UR referred Montes to welding partner
Hirebotics, a company that has incorporated UR’s
collaborative robots into the Cobot Welder: a
complete solution that includes the UR10e cobot
arm equipped with a welding torch, the Beacon
app for teaching, a welding power source, and a
versatile welding table to perform high-quality
welds on a variety of workpieces.
“At this point in the game, I really thought I
was just wasting my time,” said Montes as he
recalls getting a text om a Hirebotics co-founder,
letting him know they had received his parts. Four
minutes later, he got another text, this time with a
picture showing the part, perfectly welded up, no
gaps.
“I figured this was too good to be true and
that the entire text exchange was staged,” said
Montes, who decided to fly up to Hirebotics in
Nashville, TN, to see it first-hand. When he got
there, he was able to use Hirebotics’ app-based
interface to teach and run the Cobot Welder in
just 20 minutes with no prior robotics experience.
“I was running parts like I’ve been running robots
my whole life. Aer that, I gave them a PO, and
we got the robot in here. And that’s when the fun
started.”
From 2 to 20 inches per minute

The Cobot Welder has quickly enabled the
company to catch up on lead times and reduce
defect rates. “We went om being eight weeks
over capacity back to baseline in a matter of days,”
said Montes. He attributes this accomplishment
to the speed of the cobot that MIG welds 20
inches per minute compared to the 2-5 inches per
minute when TIG welded manually.
Montes runs his hands over a weave weld done
by the cobot and said, “Any welder worth his salt
THE ROBOT REPORT November 2023 9

DeAngelo Marine Exhaust
Collaborative Robotics of Fort Lauderdale, FL,
occupies over 30,000 sq.
feet of manufacturing and
engineering facilities suited
would have a hard time believing this is to state-of-the-art marine
a MIG weld. Once the operators started exhaust systems and diesel
toying with the settings, we realized we particulate filter systems
could get the welds to look however (DPF) production, service and
we wanted them to: fat welds, skinny repair.
welds, butt joints, lap joints—we are even | Universal Robots
building fixtures to do seam welding. He
also emphasizes the ability to dial the
cobot in to do full penetration welds:
“This was a very big concern for us. A leak
could literally sink a $100 million yacht.
But we have found no leaks by the cobot.”
ROI: one order paid off the cobot

The day the Cobot Welder hit the floor at
DeAngelo, the company received a large
order om the Coast Guard. The parts
were 12 inches in diameter, requiring a
circular weld five times. “Perfect fit for
weekends, suggesting new parts to run on
the cobot,” Montes said. “We went om fabricator. From a financial perspective,
the cobot,” said Montes. “You could see
months to just days turning that order now that the welding is performed by a
their brains just explode; now everybody’s
around. If I put dollars into it, with the machine operator rather than a fabricator,
embracing it. It’s been a big morale booster
departmental overtime and everything, our cost-per-part has plummeted.”
for our work culture.”
that first order paid off my cobot.” The
Stan Sherwin, one of the manual TIG
CEO explained how he was also able Winning over welders
welders at DeAngelo, explained how the
to shi large portions of the welding When the Cobot Welder first arrived at
cobot saves him time: “When the parts
work om fabricators, the highest-paid DeAngelo, not everybody shared Montes’
get to me, the sub-assemblies are already
employees in the shop, to the machine enthusiasm, he recalled. “We have all
welded by the cobot and it makes it a
operators that now operate the cobot. these great fabricators that see a robot
lot easier because I don’t have to try to
“Prior to the cobot, we would throw in the building. So immediately the wall
maneuver it around in a tricky position.
all the parts needed on a cart, and our is up: ‘What is this machine?’ they would
The welds by the robot look beautiful. And
fabricators would have to weld them ask.” He explained how he had them run a
it’s a lot faster.”
all together,” he said. “Once the cobot few sample parts, and kept dialing in the
was up and running, we created a welder until the welds looked right. That
Easy programming through app-based
pre-fabrication department where all was a big ‘aha moment’ for employees.
interface
these high-volume sub-assembly parts “These same people that were aaid of
Camilo Aguilar, production manager at
could get welded before they got to the the cobot, they are now calling me on the
DeAngelo, was one of the employees who
greeted the cobot with initial skepticism.
“I really had my doubts,” he admitted.
“Air-cooled MIG welding on stainless steel
and pipes? But I was wrong. To be honest,
that’s an awesome machine,” said Aguilar,
adding how he’s renamed the cobot ‘my
The Cobot Welder has baby.’ Though he had no prior robotics
enabled DeAngelo experience before the Cobot Welder
Marine Exhaust to catch arrived, the production manager is now
up on lead times and the one teaching the operators how to
reduce defect rates. The run it. “The programming is not hard; our
company went om operators pick it up so fast,” he said.
being eight weeks over As Montes put it, there was “no more
capacity back to baseline writing 10-page programs in G-code
in a matter of days. or yearlong learning curves.” Instead,
| Universal Robots operators teach the robot by simply
grabbing the robot arm and moving it
through the desired weld trajectory, adding
waypoints in Beacon, the Cobot Welder’s
app-based interface that runs on any

Collaborative Robotics
handheld device or tablet. “If you want Beacon app. “I have access to all my
to weld a circle, press circle, click three production data anywhere in real time
points—it knows that it needs to weld a through the app,” he said. “Everything is a
circle along those three points. You want number; we can see how long the arc was
to do a line? Two points, it’s that easy,” on, how much gas and wire we used. And
explained Montes, who is working on if it looks like Shift A is more profitable
fixtures that will enable the Cobot Welder because they ran faster, we can copy those
to weld 25-50 products in the same cycle. settings over to Shift B.”
Troubleshooting in real time Future applications

Having experienced long response times The Florida exhaust maker is just getting
requesting tech support for the company’s started down the cobot path. Montes pulls
CNC water jets and laser cutters, Montes out a map of the shop floor, pointing out
was positively surprised by the quick replies fabrication tables where he envisions a
he received whenever his team had a Cobot Welder going. “Our goal is to have a
question about the Cobot Welder. cobot with a UR arm on all the fabrication Nobody at DeAngelo Marine Exhaust
“Trouble-shooting on the cobot tables of our seven lead fabricators. As had any experience with robotics
is amazing,” he said. “We run the they’re jigging parts up, making sure they’re programming before the arrival of the
programming off an iPad Mini we bought hitting all their target points, they can Cobot Welder. However, the system’s
and there’s a support feature in the app, have the cobot handle the welding in the intuitive interface doesn’t require
where you can get somebody on the line meantime and just streamline everything.” yearlong learning curves. Instead,
within seconds.” He can also take pictures Jumping from welding two to 20 operators teach the robot by simply
of the issues and submit them. “I don’t inches per minute has also enabled grabbing the robot arm and moving it
need to be a welder,” he said, “but I can DeAngelo to break into new markets. through the desired weld trajectory.
send a picture and say, ‘Hey, is this the “When you’re dealing with a big engine | Universal Robots
right setting?’ And in seconds, you’ve just manufacturer, they’re not trying to pay
eliminated being down for days if not premium, custom-fabricated part prices,”
to boost production up to 10x, which is
weeks.” said Montes, explaining how he has to
what the Cobot Welder has already helped
bring his costs and lead times down
us do.”
Access to weld data from anywhere significantly to address that market and
He added with a smile, “Once more
DeAngelo’s CEO, who has a black belt in compete with manufacturers in India as
engine manufacturers figure out ‘Oh,
Six Sigma lean management and is a self- well. “In order to break into those first-fit
DeAngelo can do this now’, I don’t
professed ‘numbers nerd,’ emphasizes the OEM manufacturers where you buy an
just need more cobots; I need a bigger
production data provided by Hirebotics’ engine with my part already on it, we have
building.” RR
FLEXCODER
MOTOR & POSITION FEEDBACK FOR COBOTS
Performance data MSAC200
 Magnetic, rotary, true absolute
 Flat, compact height 10 mm
 Resolution up to 20 bit
 Large hollow shaft for cables
and media hoses
Contact us for custom specific solutions
www.siko-global.com/p/msac200
Elevate Cobot Productivity
Applied Cobotics, The Cobot Feeder
Running 24/7 on the Strength of PBC Linear Products
Steel Shafting
Ball Bearing
Pillow Block
CNC Rolled
Lead Screw
The biggest issue that this machine is solving is cobot downtime.

Without some sort of automated loading and unloading system,
cobots will inevitably sit idle, falling far short of their desired potential.
The Cobot Feeder is built to continuously feed parts to the cobot. MTB Series
Actuator
PBC Linear has implemented The Cobot Feeders with cobots on their
CNC mills and lathes that produce their signature bearings. With roughly
80 CNC machines in their shop and 15 cobot stations in operation,
The Cobot Feeder has boosted cobot production up to 1600%, and
created a more flexible manufacturing model while elevating profits.
The Cobot Feeder is easy to install, operate, and can be purchased

by itself or with a cobot. In addition, PBC Linear offers production
of custom dunnage trays for your specific parts.
6402 E. Rockton Road
Find out more at appliedcobotics.com and pbclinear.com. Roscoe, Illinois 61073 USA
+1.800.962.8979 • pbclinear.com
Design & Development
Apollo stands 5 feet 8

inches tall and weighs
160 lbs. Capable of
liing 55 lbs, Apptronik
expects the swappable
battery to power the
robot for 4 hours.
| Apptronik

Inside the development of Apptronik’s
APOLLO
HUMANOID
The company’s R&D
work on exoskeletons
and bipedal
Humanoids have been the story of 2023. Humanoids have long been relegated to
research labs, but the goalposts began to shi this year. Companies are
now creating humanoids to perform various real-world tasks.
One of those companies is Austin, Texas-based Apptronik, which has a rich history in
legged robotics. It worked on the first generation of NASA’s Valkyrie robot and multiple
locomotion for the generations of exoskeletons since its founding in 2016.
U.S. government Apptronik recently unveiled its first commercial humanoid robot, Apollo, and is
targeting tasks within warehouses and logistics facilities as the first tasks to go aer. We
and Department of recently had Apptronik’s CEO and co-founder Jeff Cardenas on The Robot Report Podcast
Defense has it primed
to discuss the company’s history, the development of Apollo and the opportunity for
humanoids in the future.
for the humanoid era. This conversation has been edited for clarity and length. To hear the interview in its
entirety, subscribe to The Robot Report Podcast anywhere you listen to podcasts.
THE ROBOT REPORT STAFF What are the origins of Apptronik?

Apptronik started in 2016. We're a spin-out om the University of Texas at Austin om a
lab called the Human-Centered Robotics Lab. Two of my co-founders are Luis Cintas, who
runs the lab at the University of Texas at Austin, and Nick Paine, who was actually Luis's
first student when he came to UT Austin and started the lab.
THE ROBOT REPORT www.therobotreport.com November 2023 15

The roots of Apptronik are really from affordability and mass manufacturing. It's We were iterating along the way to get
the lab at the University of Texas at Austin, also much more capable than the robots towards that future vision. Astra really
but they largely come out of the DARPA we've built in the past, taking everything represented one of the first productized
Robotics Challenge. Luis and Nick worked we've learned and building the robot we humanoids we'd ever built. So it was the
on the Valkyrie robot with the NASA always dreamed of building. most polished of the systems we built
Johnson Space Center. Valkyrie was one of up to that point. And we have done full
the most advanced electric humanoids at Can you detail Apptronik’s product humanoids prior to that, we'd also done
the time. history leading up to Apollo? just bipeds, and prior to that a handful
We now have about 85 full-time What we're doing as a company is of R&D bipeds to crack the dynamic
employees. We've been working on this iterating on our technology roadmap. locomotion problem.
problem of getting a humanoid out of the How do we get from Valkyrie, which was We realized the real demand was for
lab and into the real world for the better about 300 pounds, six feet two inches more dexterous manipulation or more
part of the last decade. Apollo represents tall and a multimillion-dollar system, to versatility in manipulation. And so when we
our eighth iteration of a humanoid. a sub-$50,000, highly robust, scalable, thought about building the first product,
It's much more robust, designed for humanoid? we focused on this idea of building a dual-

CONNECT
So Astra was initially deployed TECHNOLOGY
WITH
on a wheeled, mobile base,
Apollo could
but then we started to make
eventually be outfitted
with dexterous
hands, but the initial
some breakthroughs on the
dynamic locomotion ont.
We brought in Gerardo Bledt,
CONFIDENCE
applications will only
who came om Sangbae
require a simple 0-1
Kim's lab at MIT and had
DoF hand. / / WWW . H A RW I N . C O M
worked on the Mini Cheetah
| Apptronik quadruped. He had done
a lot of great work on model
predictive control for quadrupeds.
We started to bring in the work that
was being done there in quadrupeds and
convert that to bipeds. That work started
in 2020, and we started to see bipedal
locomotion maturing to the point where
we felt it could be deployed and start to
realize the vision of the full humanoid,
which is a dual-arm, bipedal system.
Why are so many companies now

developing commercial humanoids?
I think there are a number of reasons why
humanoids are getting a lot of interest
right now. The reason why customers
are interested is pretty straightforward.
Their entire process is built for humans,
and they've adopted robots today. This
is largely in manufacturing and logistics,
where you've seen the most uptake of
robots. There's a lot of spot automation
that's happening out there in that domain.
There are robots that can do one or two
things.
The big companies adopting this
technology have 10-20 different vendors,
and each vendor does one particular
task. This is becoming difficult for them
arm, mobile manipulator and building to manage. There’s also a lot of work that
a best-in-class system there that was has to be done to fit existing automation
largely performance optimized. into their workflow. So the idea of a
That was Astra, and we delivered a multipurpose, or more versatile, system
handful of those to customers and had that can easily retrofit into an existing
them out in the world. A handful of them workflow is attractive.
have been successful pilots along the way But what's made it particularly Harwin’s connector products are proven to
in partnership with some other groups. It attractive to these customers is that they're perform in extreme conditions, with shock,
was eye-opening for us to get the system seeing enough progress that they say, “OK,
vibration and temperature range rigorously
out there. It proved out some of the early this is now here. And this makes a lot of
tested.
ideas we had about the viability of the sense to us for a number of reasons.”
technology and where it was at. I always look toward another
WITH OUR QUALITY, SERVICE, SUPPORT,
Once we felt like we had a good line technology trend to see what's going
AND HIGHLY RELIABLE PRODUCTS, YOU
of sight on the manipulation problem, we to make sense in a new field. I use the
CAN DEPEND ON HARWIN.
started to dial up the mobility problem. computer analogy to explain what a

humanoid really is. In the early days of computers, you

had special-purpose computers. Then you went om
more special-purpose computers to mainames. But
Apptronik said what it took for computers to reach the market and
it is beginning to reach higher density and true commercialization
pilots for Apollo was the move om the mainame to the personal
and is targeting computer - a general-purpose hardware platform
commercial that was a soware update away om doing
availability by the something new and different.
end of 2024. The PC is where computers had their breakout
moment. It seemed crazy back in the 90s when you
| Apptronik
had Bill Gates saying one day in every home you're
going to have a computer on every desk. But look at
where we are now; everyone's carrying a computer
around in their pocket or on their wrist.
I view humanoids as personal computers in the early
1980s. What we have to find are the initial applications
for humanoids. For this general-purpose platform to
be viable out in the market, you'll add functionality on
top of it. I tell customers that you can either have 1,000
robots that each do one thing, or you can have one robot
that does 1,000 different things.
What are the features and capabilities of Apollo?

Apollo is 5 feet 8 inches tall and weighs 160 pounds with
the battery. It's got onboard compute, it lis about 55
pounds and is targeted at OSHA (Occupational Safety
and Health Administration) specs. Initially, we're targeting
it to have a four-hour runtime with swappable batteries.
Long term, we want it to have a 22-hour per day, seven-
day-a-week uptime. And we believe the way to get there
THE RIGHT STAMPING. is with swappable batteries.
Apollo is one of the first systems we've built with
THE RIGHT WASHER. swappable batteries in it. It's taking all the ideas that
RIGHT NOW.
we've learned om all the different systems that
we've built [before this], including humanoids, mobile
manipulators and exoskeletons, putting them all
together.
We're aiming to build Apollo for less than the price
BOKER’S WILL BE THERE. For over 100 of many cars that are on the market today, and we
years, nearly every industry across the don't need an obscene scale to be able to do that.
globe has trusted Boker’s to provide We're building it in a fundamentally different way om
quality components, world-class what we've seen [in] other systems that are [currently
service and fast delivery. released]. We're borrowing ideas om other machines
that are out in the world that are produced at a scale
much more affordable than robots are today. But all
SUBMIT YOUR PART SPECS & that's coming together in Apollo.
Get a Fast Quote Apollo is designed to have hands. We've partnered
with several other groups on hands in the past. We've
partnered with some folks who are really pushing the
(800) -WASHERS bokers.com
boundaries of dexterous manipulation. We've also
purchased hands om groups that are building more
affordable robotic prosthetics. Our initial strategy is to
basically partner on dexterous manipulation.
The first use cases we're targeting for Apollo
require only gross manipulation. In terms of where the
technology is today, I think long term a humanoid has to
18 November 2023 THE ROBOT REPORT

have hands. Most of the work that humans We'll show and demonstrate videos
do in the world today does involve some
level of dexterity.
of Apollo with full hands, showing the
capabilities and dexterity. The problem We're aiming to
The exciting thing for us, in terms of when you look at commercialization is
where we can apply the robots today with the rate. The most interesting approach to build Apollo for
the technology that exists right now, is in dexterous manipulation that we've seen is
the gross manipulation domain, meaning
things where you're using two hands to
using teleop to train models, which allows
you to get a dexterous manipulator out less than the price
grasp something at once. That's largely in into the world today. The economics of that
logistics and material handling. are tough when you start to look at teleop of many cars that
You'll see us move across the spectrum initially. We believe autonomy is ultimately
om gross manipulation to finding our
dexterity over time. We will use different
going to win the day, and we are focused
on autonomy for the initial applications are on the market
effectors for that as we initially deploy that we're deploying and delivering on over
[Apollo], so we don't need a five-finger
hand [at launch]. For initial
the next one to two years. today, and we don't
deployments, we can use one
degree of eedom in the end
How did Apptronik
decide which types of need an obscene
effector that allows us to solve applications to go aer
all the initial use cases that
we're looking at, and then
with Apollo?
Just like with any big
scale to be able to
move into finer dexterity over
time.
problem, you break the
problem down and start do that.
as simply as you can.
Apollo represents
the pinnacle of
more than 13
generations of
electric actuators
developed by
Apptronik.
| Apptronik

Then you build in complexity. The way Apptronik has developed a novel
we view the go-to-market strategy electric actuator for Apollo. How did
for humanoids is to build a general- this technology come to be and how
purpose robot that can do many of the will it impact Apollo?
tasks humans can do but don’t want The focus of Nick’s Ph.D. was around
to do. electric actuators for legged systems. So
But before a system can be general- this has been his body of work in grad
purpose, it has to be multipurpose school and is now a big part of the DNA
and do at least three to four tasks in of Apptronik. We made a big bet early
production out in the world. Before it on with electric actuation. We thought
can be multipurpose, it's got to at least electric actuation was going to be the
do one of those tasks reasonably well. future.
So our approach is to start by picking All of our actuators are
one initial task in material handling. We force-controlled as well, which
have a particular application that we're we thought was going to be
focused on, basically handling cases an important thing. We've
or boxes, and moving them om one done over 35 unique electric
place to another. If you can just get to actuators up to this point.
multipurpose, that's enough for many So a tremendous amount of
of the logistics use cases and customers iteration. Some of those are
we're talking to today. small, medium, and large
members of a common
How large of an opportunity is this family of actuators. So
box-moving application?
To give you an idea of scale, there are
about 675,000 unfilled logistics jobs in
the U.S. today. So there's a huge number
of open jobs in the logistics market. If
you just look at case handling, there
will be about 200 billion cases that
are picked globally by 2025. There's a
massive opportunity. The thing that was
exciting for us was that we realized the
technical barrier to entry was actually
much lower than we thought. We
thought we were going to have to get to
dexterous manipulation for humanoids
to be viable. We saw that there was
demand if we could just move boxes,
cases, or totes in a warehouse. And
that's something that we can do today.
That started to motivate us towards
200 billion cases
pushing Apollo to the foreont of our they're not all completely
will be moved
commercialization plan so that we can unique, but you learn
each year by 2025,
get robots out there to start working a lot.
representing
in real-world use cases and build om What we've landed
a massive
there. There's a lot of potential for on aer all of that is the
opportunity for
humanoids, but very few, if any, have Goldilocks, if you will, of
Apollo and other
been deployed commercially. That’s the performance and cost. The
humanoids.
litmus test. new actuators we've put into
The next big thing for us is to start Apollo have about a third | Apptronik
moving om demos to pilots and then fewer components than the
to real deployments. There's a handful previous actuators we've built,
of folks that are pushing that forward, which take about a third of the
and we have a lot of respect for the assembly time.
other players that are here in the space And more importantly, they're
with us. solving a big problem in robotics

readycable ®
cable assemblies
MILLIONS OF FEET IN STOCK
FLEXIBILITY FOR DYNAMIC APPLICATIONS
DESIGNED TO PREVENT CORKSCREWING
NO MINIMUM LENGTH REQUIREMENT
UL-VERIFIED GUARANTEE UP TO 36 MOS.
Meets 20+ manufacturer standards

• In stock & ships in as little as 24 hours • Entire assembly from single source
• No minimum order quantity required • Online tool to estimate cable lifetime
• Wide range for lowest cost solution • Available fully installed within e-chain
®
around the supply chain. One of the big humanoids have to be collaborative
challenges is being driven by cost and to deliver on the value proposition.
how many units we can deliver to the There are all sorts of new committees
market. The robotics industry requires coming together to think about safety
high-precision components, in particular for humanoids.
harmonic drives. There are only a handful There are two ways we handle
of companies that have ever been able to safety. The system itself is force-
scale those up to high volumes. So one of controlled, and so it works like a
the things that we were focused on was: collaborative robot might work: it can
how do you get harmonic drives out of the respond to an impact. The second way
system altogether? How do we get rid of is with vision, soware and behaviors.
these proprietary, expensive components The robot basically has this field of
that are not good for unstructured vision around it where if you get close,
applications and are also pretty expensive, the robot can slow down. And if you
relatively speaking? get really close to it, it can come to a
With Apollo, we've finally achieved that. stop.
Usually, when you hit everything, there's A big question is what do you
a trade-off. But the exciting thing about do if the robot falls? Right now we
Apollo is we actually have a better system have a safety procedure where the
– it's higher performance, we can achieve robot basically tucks up when it
higher speeds, and it's more robust to falls to mitigate the risk. But there's
external impacts. a lot of work that we're doing with
It's also more affordable than the our customers and there's different
systems we built in the past. So there philosophies about how folks want
are some trade-offs that you make to approach that. Some groups don't
when you increase the complexity of the want the robot to slow down, while
controls when you're building a system others are more concerned that there
like this. We're not using serial chain rotary are a lot of dangerous machines out
actuators, as many of the systems in the in the world today. And if you look at
past have used. So we had to build new manufacturing or logistics today, think
soware and solve some new problems to about a forkli or any of the machinery
bring a system like this online. they have in manufacturing relative
But the benefits have really outweighed to a humanoid - you're just thinking
that and a lot of that tech risk is now about how to mitigate that risk.
behind us. From a technology standpoint, I think it's a crawl-walk-run
we're really proud of what we've come up situation where, initially, we just want
with and what we've delivered. We really to get humanoids out of labs and into
think that it's a system that only we could real production environments. We
have built with all the experience that can mitigate how closely they interact
we've had over the last several years, and with humans. Ultimately, we want
all the systems we built leading up to it. them to be seamlessly integrated by
working with the industry as a whole.
Safety is a big concern with humanoids. We want to work with the other folks
How is Apptronik making Apollo safe to in this domain to determine the safety
work around? standards and what makes sense and
Safety is really important. First and that will continue to progress over the
foremost, it's a big focus for us at coming years. RR
Apptronik. And we think we're well
positioned as we’ve done so much work on
high-fidelity force control.
For the customers that we're dealing
with and initial deployments, the
easy way to solve this is to not
have humans around the
system during the pilot
phase. But ultimately,
22 November 2023
Control your entire
robotic fleet
from a web browser
in real-time
CLOUD GROUND CONTROL

Cloud Ground Control (CGC) is a cloud-based command
and control solution for operators and manufacturers of
uncrewed air, land and sea vehicles.
Connect your DJI drones via our mobile app, or any other
vehicles using CGConnect – our cellular micro-modem.
Scan the QR code or visit

www.cloudgroundcontrol.com
Researchers are
exploring how large
language models can
be applied to robotics
design, model
training, simulation,
control algorithms
and more.
| Adobe Stock
Teaching robots new tricks

WITH GENERATIVE AI STEVE CROWE • EXECUTIVE EDITOR • ROBOTICS
A new AI agent developed by NVIDIA

Research that can teach robots
complex skills has trained a Shadow Robot
robots to open drawers and cabinets, toss
and catch balls, and manipulate scissors,
among many other tasks.
development platform for building 3D tools
and applications based on the OpenUSD
amework. Eureka, itself, is powered by the
hand to perform rapid pen-spinning tricks. NVIDIA recently published its Eureka GPT-4 large language model (LLM) that
NVIDIA claimed it is the first time a robot research, which includes a paper and was created by OpenAI.
can do this as well as a human can. the project’s AI algorithms. Robotics “Reinforcement learning has enabled
The trick is one of nearly 30 tasks developers can experiment with these impressive wins over the last decade, yet
that robots have learned to accomplish algorithms with using NVIDIA Isaac Gym, many challenges still exist, such as reward
thanks to Eureka, which NVIDIA said a physics simulation reference application design, which remains a trial-and-error
autonomously writes reward algorithms for reinforcement learning research. Isaac process,” said Anima Anandkumar, senior
to train robots. Eureka has also taught Gym is built on NVIDIA Omniverse, a director of AI research at NVIDIA and an

Infinite
Possibilities.
For more information, visit
pepperl-fuchs.com
SmartRunner Explorer 3-D
Pick and place applications require special

technology for detection and positioning. When
attached to the articulated arm, the SmartRunner
Explorer 3-D with stereo vision enables accurate
object placement for an exact gripping point.
Pepperl+Fuchs Vision Library Toolbox includes
ROS (Robot Operating System) drivers.
author of the Eureka paper. “Eureka is

a first step toward developing new
algorithms that integrate generative
and reinforcement learning
methods to solve hard tasks.” The ability to spin a
pen in its hand is one
AI trains robots of nearly 30 tasks
Eureka-generated reward robots have learned to
programs, which enable trial- accomplish thanks to
and-error learning for robots, a new AI agent om
outperform expert human- NVIDIA called Eureka.
written ones on more than
| NVIDIA
80% of tasks, according to the
paper. This leads to an average
performance improvement of more
than 50% for the bots.
The AI agent taps the GPT-4 LLM and
generative AI to write soware code that
rewards robots for reinforcement learning.
It doesn’t require task-specific prompting
or predefined reward templates.
Using GPU-accelerated simulation in
Isaac Gym, Eureka can quickly evaluate
the quality of large batches of reward
candidates for more efficient training.
Eureka then constructs a summary of
the key stats om the training results and
instructs the LLM to improve its generation
of reward functions. In this way, the AI
is self-improving. It’s taught all kinds of
robots — quadruped, bipedal, quadrotor, computer graphics, computer vision, self- trained a baseline policy om scratch using
dexterous hands, cobot arms and others — driving cars and robotics. EUREKA reward without the first-stage
to accomplish all kinds of tasks. pre-training. Eureka fine-tuning quickly
The research paper provides in- Inside the pen-spinning trick adapted the policy to successfully spin the
depth evaluations of 20 Eureka-trained NVIDIA said using the Shadow Robot pen for many consecutive cycles along a
tasks, based on open-source dexterity hand to spin a pen helped it investigate specified spinning axis. In contrast, neither
benchmarks that require robotic hands whether EUREKA can be used to solve a pre-trained or learning-om-scratch
to demonstrate a wide range of complex novel and challenging dexterous task. This policies completed even a single cycle
manipulation skills. task is highly dynamic and requires the of pen spinning. In addition, using this
“Eureka is a unique combination of robot hand to continuously rotate a pen EUREKA fine-tuning approach, NVIDIA said
large language models and NVIDIA GPU- to achieve some pre-defined spinning it also trained pen spinning policies for a
accelerated simulation technologies,” said patterns for as many cycles as possible. variety of different spinning configurations.
Linxi “Jim” Fan, senior research scientist NVIDIA used a curriculum learning
at NVIDIA, who’s one of the project’s approach to break down the task into Improving with human feedback
contributors. “We believe that Eureka will manageable components that could be NVIDIA said it readily incorporates human
enable dexterous robot control and provide independently solved by EUREKA; similar feedback to modi its rewards for results
a new way to produce physically realistic approaches have been found successful more accurately aligned with a developer’s
animations for artists.” for other coding LLM applications to vision. NVIDIA said the reason for this is
It’s breakthrough work bound to decision making. Specifically, NVIDIA first that humans have something Eureka lacks.
get developers’ minds spinning with instructed EUREKA to generate a reward "Human designers are generally
possibilities, adding to recent NVIDIA for re-orienting the pen to random target knowledgeable about relevant state
Research advancements like Voyager, configurations. Then, using this pre- variables but are less proficient at
an AI agent built with GPT-4 that can trained policy, NVIDIA fine-tuned it using designing rewards using them," NVIDIA
autonomously play Minecra. the EUREKA reward to reach the sequence said. "This makes intuitive sense as
NVIDIA Research comprises hundreds of pen-spinning configurations. identiing relevant state variables that
of scientists and engineers worldwide, To demonstrate the importance of should be included in the reward function
with teams focused on topics including AI, curriculum learning, the researchers also involves mostly common sense reasoning,

but reward design requires specialized In contrast, EUREKA adeptly generates TRI’s robot behavior model learns om
knowledge and experience in RL." ee-form, white-box reward code and haptic demonstrations om a teacher,
Reward engineering is a long- effectively improves in-context. combined with a language description
standing challenge in reinforcement of the goal. It then uses an AI-based
learning. The most common reward Just getting started diffusion policy to learn the demonstrated
design method is manual trial-and-error. NVIDIA is one of many companies skill. This process allows a new behavior to
Inverse reinforcement learning (IRL) infers exploring how LLMs and Generative be deployed autonomously om dozens of
reward functions om demonstrations, AI can impact robotics development. demonstrations.
but it requires expensive expert data For example, Toyota Research Institute TRI’s approach to robot learning is
collection, which may not be available, (TRI) recently unveiled how it is using agnostic to the choice of teleoperation
and outputs non-interpretable black- Generative AI to help robots learn new device, and it said it has used a variety
box reward functions. Several prior dexterous behaviors om demonstration. of low-cost interfaces such as joysticks.
works have studied automated reward TRI said this new approach “is a step For more dexterous behaviors, it is
search through evolutionary algorithms. towards building ‘Large Behavior Models taught via bimanual haptic devices with
These early attempts are limited to (LBMs)’ for robots, analogous to the position-position coupling between the
task-specific implementations of LLMs that have recently revolutionized teleoperation device and the robot.
evolutionary algorithms that search over conversational AI.” Position-position coupling means
only parameters within provided reward At press time, TRI had already taught the input device sends measured pose
templates. robots more than 60 difficult, dexterous as commands to the robot and the robot
Recent works have also proposed using skills using the new approach. Some of tracks these pose commands using
pre-trained foundation models that can these skills include pouring liquids, using torque-based Operational Space Control.
produce reward functions for new tasks. tools and manipulating deformable The robot’s pose-tracking error is then
Most of these approaches output scalar objects. These were all realized, according converted to a force and sent back to the
rewards that lack interpretability and to TRI, without writing a single line of input device for the teacher to feel. This
do not naturally admit the capability to new code; the only change was supplying allows teachers to close the feedback loop
improve or adapt rewards on-the-fly. the robot with new data. with the robot through force and has been
critical for many of the most difficult skills “Existing Large Language Models The team added a simple Spot SDK service
we have taught. possess the powerful ability to compose to communicate audio with the EAP 2
TRI admitted that “when we teach a concepts in novel ways and learn om payload.
robot a new skill, it is brittle.” Skills will single examples,” TRI said. “In the past Now that Spot had the ability to
work well in circumstances that are similar year, we’ve seen this enable robots to handle audio, the team needed to give
to those used in teaching, but the robot generalize semantically (for example, pick it conversation skills. They started with
will struggle when they differ. TRI said the and place with novel objects). The next big OpenAI’s ChaptGPT API on gpt-3.5, and
most common causes of failure cases we milestone is the creation of equivalently then upgraded to gpt-4 when it became
observe are: powerful Large Behavior Models that fuse available. Additionally, the team did tests
• States where no recovery has been this semantic capability with a high level of on smaller open-source LLMs.
demonstrated. This can be the result physical intelligence and creativity. These The team took inspiration om research
of demonstrations that are too clean. models will be critical for general-purpose at Microso and prompted GPT by making
• Camera viewpoint or background robots that are able to richly engage with it appear as though it was writing the next
significant changes. the world around them and spontaneously line in a Python script. It then provided
• Test time manipulations that were not create new dexterous behaviors when English documentation to the LLM in
encountered during training. needed.” the form of comments and evaluated
• Distractor objects, for example, Boston Dynamics recently used the output of the LLM as though it were
significant clutter that was not present ChatGPT, and other AI models, as a proof Python code.
during training. of concept and turned its Spot quadruped, The Boston Dynamics team also gave
which is typically used for inspections, the LLM access to its SDK, a map of the
Part of TRI’s technology stack is Drake, into a robot tour guide. The demo the tour site with 1-line descriptions of each
a model-based design for robotics team planned required Spot to be able to location, and the ability to say phrases or
that includes a toolbox and simulation speak to a group and hear questions and ask questions. They did this by integrating
platform. Drake’s degree of realism allows prompts om them. Boston Dynamics 3D a VQA and speech-to-text soware.
TRI to develop in both simulation and in printed a vibration-resistant mount for a They fed the robot’s gripper camera and
reality and could help overcome these Respeaker V2 speaker. They attached this ont body camera into BLIP-2, and ran it
shortcomings going forward. TRI’s robots to Spot’s EAP 2 payload using a USB. in either visual question answering mode
have learned 60 dexterous skills already, Spot is controlled using an offboard or image captioning mode. This runs about
with a target of hundreds by the end of computer, either a desktop PC or a laptop, once a second, and the results are fed
2023 and 1,000 by the end of 2024. which uses Spot’s SDK to communicate. directly into the prompt.
Using its Generative

AI approach, Toyota
Research Institute has
taught robots more than
60 dexterous behaviors
like peeling vegetables,
using hand mixers,
preparing snacks, and
flipping pancakes.
| Toyota Research Institute

To give Spot the ability to hear, the “Who is Marc Raibert?” Raibert is the
team fed microphone data in chunks to founder of Boston Dynamics. Yet, the
OpenAI’s whisper to convert it into English robot didn’t know the answer and told A NEW GENERATION OF
text. Spot waits for a wake-up word, like the team that it would go to the IT help ROTARY ENCODERS
“Hey, Spot” before putting that text into desk and ask, which it wasn’t programmed
the prompt, and it suppresses audio when to do. The team also asked Spot who its
it is speaking itself. parents were, and it went to where the
Because ChatGPT generates text- older versions of Spot, the Spot V1 and Big
based responses, the team needed to run Dog, were displayed in the office.
these through a text-to-speech tool so These behaviors show the power
the robot could respond to the audience. of statistical association between the
The team tried a number of off-the-shelf concepts of “help desk” and “asking a
text-to-speech methods, but they settled question,” and “parents” with “old.” They
on using the cloud service ElevenLabs. To don’t suggest the LLM is conscious or
help reduce latency, they also streamed intelligent in a human sense, according to
the text to the platform as “phrases” the team. Meet POSITAL’s Updated and
in parallel and then played back the The LLM also proved to be good at Improved IXARC Encoders
generated audio. staying in character, even as the team gave
The team also wanted Spot to have it more absurd personalities to try out.
more natural-looking body language. So While the LLM performed well, it did New TMR sensor technology
it used a feature in the Spot 3.3 update frequently make things up during the tour.
that allows the robot to detect and For example, it kept telling the team that and upgraded processors offer
track moving objects to guess where the Stretch, Boston Dynamics’ logistics robot, enhanced performance and
nearest person was, and then have the is for yoga.
robot turn its arm toward that person. Moving forward, Boston Dynamics better energy efficiency.
Using a lowpass filter on the generated plans to continue exploring the
speech, the team was able to have the intersection of artificial intelligence and Incremental encoders are
gripper mimic speech, sort of like the robotics. To them, robotics provides a
mouth of a puppet. This illusion was good way to “ground” large foundation programmable for extra versatility:
enhanced when the team added costumes models in the real world. Meanwhile, these Resolution and communications
or googly eyes to the gripper. models also help provide cultural context,
interfaces are can be easily
The team noticed new behavior general commonsense knowledge, and
emerging quickly from the robot’s very flexibility that could be useful for many customized to meet your exact
simple action space. It asked the robot, robotic tasks. RR
requirements.
Muliturn absolute models feature

updated Wiegand sensors and a
new ASIC for optimized battery-
free rotation counting
More NEXTGEN product

announcements coming soon!
A diagram of the overall system used to turn Boston Dynamics’ Spot quadruped into
a tour guide that used ChatGPT and other AI models. | Boston Dynamics
www.posital.com

| Adobe Stock
Humanoids getting their feet wet
IN LOGISTICS
ASH SHARMA • MANAGING DIRECTOR • INTERACT ANALYSIS
Humanoids offer the

Amazon recently started to test a
humanoid robot, Digit, in
its warehouses, raising esh questions
fulfillment centers with a wide product
mix or fluctuating demand, the flexibility
of humanoids could deliver a solution to
potential flexibility about how swily humanoids will be the ongoing labor and skills crisis in the
used in logistics. Made by Agility Robotics, logistics industry. For example, humanoids
and scalability to be Digit can grasp and li objects, and it could be dropped into the workforce
used within existing will start by shiing empty tote boxes as
Amazon continues to explore new ways of
during seasonal peaks in demand without
requiring substantial operational changes,
warehouses alongside automating its warehouses. unlike other automated technologies where
humans to help pick,
Warehousing offers the perfect large changes to warehouse workflows are
combination of repetitiveness and required.
move and sort goods. menial work, coupled with a lack of One early application for humanoids is
standardization and a lack of uniformity of likely to be trailer unloading, as it is simple,
things handled. For companies operating repetitive and physically demanding.

Amazon is initially
Unlike other robots, humanoids offer the
testing Digit’s ability
additional benefit of being flexible enough
to move empty
to take on multiple different tasks in a
tote boxes onto a
facility, rather than being limited to a single
conveyor belt.
process or workflow.
Despite the current media storm | Amazon
around humanoids, this change will
not happen overnight, as pilot projects
can take many months, or even years,
to reach completion. Robots are in high
demand within the logistics sector in
light of severe labor and skills shortages,
and volatile demand. However, while the
widespread use of humanoids within
warehouses is certainly a possibility, it is deployment of humanoid robots, as well as
not an inevitability and we may well find replacing the most “menial, mundane and off despite Amazon’s latest move. Pilots
that other robots are better suited to repetitive” tasks. Developed by Amazon- of new technology such as this can take
specific tasks and come with fewer ethical backed Agility Robotics, Digit is described upwards of 18 months and, if successful,
problems, particularly in terms of perceived as “a mobile manipulator solution.” rollout tends to be in small steps. However,
role replacement. Standing 5 9in (175cm) tall, Digit can li Amazon has always been a leader in its
and carry up to 35lbs (16kg), crouch, reach, use of robotics and the rest of the industry
Warehouses ripe for humanoids, but pick up and put down. tends to follow (or fail!), so this pilot could
challenges persist Tye Brady, chief technologist at Amazon be the catalyst for humanoid robot uptake
Reports claim Amazon’s decision to Robotics, told reporters in Seattle that the in the coming years.
trial Digit raises concerns about the move does not mean job cuts at Amazon Is it possible for the use of humanoids
displacement of human workers. Other and people are “irreplaceable” to the to be hyped too much? And given the
automated systems are ‘unhuman’ enough business because of their “ability to think representations of humanoid robots we
not to cause unease to the same extent as at a higher level, the ability to diagnose oen see in popular culture, will this shape
humanoid workers. problems.” public opinion? Can robots look too much
In response to fears around job loss, Other humanoids are in development like people? It is true that the more lifelike
Amazon has emphasized the “hundreds om companies such as Figure and humanoid robots are, the more they are
of thousands of new jobs” that have been Boston Dynamics. Tesla’s Optimus Robot labor replacement personified.
created as a result of its use of robotic can sort objects autonomously as it can It is too early to tell whether in the
systems, including “700 categories of new self-calibrate its arms and legs, while the long term humanoid robots will become
job types, in skilled roles, which didn’t exist commercial launch of Apptronik’s Apollo is a common sight in warehouses around
within the company beforehand.” The expected to take place in late 2024. Videos the world – much will depend on
global warehousing sector, particularly of the humanoid robot have already shown how successful these early pilots are.
within the U.S., has been facing critical it walking, case picking, palletizing and Humanoids offer the potential flexibility
shortages of labor and skills in recent years. unloading trailers. and scalability to be used within existing
A poll published earlier this year by MHI In reality, warehouse automation has warehouse operations alongside the
and Deloitte revealed hiring and retaining been in place for decades now, including human workforce, helping to pick, move
qualified workers and talent shortages autonomous mobile robots (AMRs) working and sort goods. They are the next logical
were the leading challenges for U.S. supply alongside human workers and carrying out step in the evolution of the multibillion-
chain leaders, with many planning to invest many of the menial, physically demanding dollar robotics industry, as customers seek
in robotics and automation in the near jobs. Automated storage and retrieval solutions that can be used across multiple
future. systems are capable of order picking at workflows and applications.
Digit has been designed for warehouse a much faster rate and are being used The flexibility and scalability
automation where the complexities of alongside human workers to increase humanoids offer could be a possible
human thought and movement are less throughput. answer to ongoing labor and skills
important than improving throughput and shortages. However, it does not come
filling skills and labor gaps. With almost 1.5 How soon will humanoids become the without complications and it is yet to
million humans employed across Amazon’s norm in warehouses? be seen whether these will be easily
operations, the company is keen to stress It looks as though the widespread use of overcome to see their rapid deployment in
the potential to create jobs through the humanoids in the warehouse is some way warehouses. RR

Sensors
VMT is now using a robot

with a vision system to
load and unload parts
om containers. It said this
is a difficult technological
challenge because the
containers come om
different manufacturers,
are of different types and
can vary in dimension.
3D cameras enable
AUTOMATIC LOADING
of pressed parts
THE ROBOT REPORT STAFF
Four 3D cameras from Robots do monotonous workflows and less pleasant, repetitive tasks with brilliance.
Combined with image processing, they become “seeing” and reliable
IDS Imaging each record supporters of humans. They are used in quality assurance to check components, help
with the assembly and positioning of components, detect errors and deviations in
a part of the entire production processes and thus increase the efficiency of entire production lines.
image field, resulting An automobile manufacturer is taking advantage of this to improve the cycle time
of its press lines. Vision Machine Technic Bildverarbeitungssysteme GmbH (VMT) om
in data from multiple Mannheim, Germany developed a robot-based 3D measuring system, FrameSense,
perspectives for a higher for fully automatic loading and unloading of containers. Pressed parts are safely and
precisely inserted into or removed om containers. Four Ensenso 3D cameras om IDS
quality 3D point cloud. Imaging Development Systems GmbH provide the basic data and thus the platform for
process automation.

WISE Design | WISE Guidance | WISE Investment
ROBOT TRANSFER UNITS BUILT ON

DUALVEE® MOTION GUIDE TECHNOLOGY
Support and transfer robot arms of any size with Bishop-
Wisecarver®’s suite of RTUs. We provide reliable, long-lasting
RTUs and 7th axis systems for all your favorite brands of
cobots and industrial arms.
VISIT WWW.BWC.COM
WE’RE THE WISE CHOICE
Choose solutions that excel and endure in the most extreme environments and
conditions. Easy to order, quick to turn around, and with all the support you
need to complete your project on time.
Sensors
Application Four Ensenso C

The workflow FrameSense is cameras capture
designed to automate is part of the contours of the
many manufacturing operations. stacking containers
A component comes out of a for VMT.
machine - here a press - and | IDS Imaging
runs on a conveyor belt to a
container. There it is stacked. As
soon as the container is full, it is
transported to the next production step -
assembly into a vehicle.
Up to now, employees have been
responsible for loading the containers.
This actually simple subtask is more
complex than one might think at first
glance. In addition to the actual insertion
process, the first step is to determine the
appropriate ee space for the part. At the
same time, any interfering factors, such as
interlocks, must be removed and a general
check of the “load box” for any defects
must be carried out.
All these tasks are now to be taken
over by a robot with a vision system - a the respective measuring
technological challenge. This is because container. This approximately
the containers also come om different is the only way to 1.5 x 2 x 1.5 meters
manufacturers, are of different types ensure process-reliable (D x W x H). Two of the
and thus vary in some cases in their and collision-ee path guidance of the cameras focus on one container. This
dimensions. loading robot. All this has to be integrated results in data om two perspectives each
into the existing production process. for a higher information quality of the 3D
Type, shape and position inspection with Time delays must be eliminated and the point cloud. These point clouds of all four
3D cameras positioning of the components must be sensors are combined for the subsequent
For fully automatic loading and unloading, accurate to the millimeter. evaluation.
the position of several relevant features of To counter this, VMT uses four 3D In the process, registrations of relevant
the containers must be determined for a cameras per system. The four sensors each features of the container take place in
multi-vector correction of the robot. The record a part of the entire image field. ROIs (Regions of Interest) of the total
basis is a type, shape and position check of This can consist of two containers, each point cloud. A registration is the exact
positioning of a feature using a model in
all 6 degrees of eedom. In other ROIs,
interference contours are searched for
which could lead to collisions during
loading. Finally, the overall
picture is compared with a
stored reference model. In
When inserting the this way, the containers
components into can be simultaneously
the comb strips of checked for their
the racks, the robots condition and position
have to work with in a fully automated
millimeter precision. manner. Even deformed
| IDS Imaging or slanted containers
can be processed. All this
information is also recorded
for use in a quality management
system where the condition of all
containers can be traced. The calibration

as well as the consolidation of the measurement data and
their subsequent evaluation are carried out in a separate
IPC (industrial computer) with screen visualization,
operating elements and connection to the respective
robot control.
The main result of the image processing solution
is the multi-vector correction. In this way, the robot is
adjusted to be able to insert the component at the next
possible, suitable deposit position. Secondary results are
LOW-VOLTAGE
error messages due to interfering edges or objects in the
container that would prevent filling. Damaged containers
that are in a generally poor condition can be detected
GEARMOTORS
and sorted out with the help of the data. The entire
image processing takes place in the image processing
soware MSS (Multi Sensor Systems) developed by VMT.
FrameSense is designed to be easy to use and can also be
converted to other components directly on site.
for AGV/AMR Applications
Robust 3D camera system
On the camera side, VMT relies on Ensenso 3D cameras -
initially on the X36 model. The current expansion stage of
FrameSense is equipped with the Ensenso C variant. The
reasons for the change are mainly the better projector
performance - thanks to a new projection process - as
well as a higher recording speed. In addition, the Ensenso
C enables a larger measuring volume. This is an important
criterion for FrameSense, because the robot can only reach
the containers to be filled up to a certain distance.
The specifications of the Ensenso C correspond
exactly to VMT's requirements, as project manager and
technology manager Andreas Redekop explained. "High
projector performance and resolution together with fast
data processing were our main technical criteria when
selecting the camera. The installation in a fixed housing
was also an advantage.”
The Ensenso C addresses current challenges in the
auomation and robotics industry. Compared to other
Ensenso models, it provides both 3D and RGB color
information. Customers thus benefit om even more
meaningful image data. The housing of the robust 3D
camera system meets the requirements of protection class
IP65/67. It offers a resolution of 5 MP and is available with
baselines om current to approx. 455 mm. This means
that even large objects can be reliably detected. The
camera is quick and easy to use and addresses primarily
large-volume applications, e.g. in medical technology,
logistics or factory automation.
Outlook
By automatically loading and unloading containers
and the integrated 3D container inspection, manual Our efficient, high-performance low-voltage
workstations can be automated with the help of brushless DC (EC) gearmotors are available
FrameSense. Against the background of the shortage of with brakes, encoders, special connectors
skilled workers, the system can thus make an important and wire harnesses. Call today with your
contribution to process automation in the automotive #AGV #AMR gearmotor questions!
industry, among others. It meets the prevailing challenges
bodine-electric.com
info@bodine-electric.com | 7 7 3 . 47 8 . 3 515 (USA )

THE ROBOT REPORT November 2023 35
S U M M I T & E X P O
Medtech conversations to inspire

the next generation of devices
Sponsorship opportunities are available for future DeviceTalks and Robotics programs.
For more information, contact Colleen Sepich. 857.260.1360 | csepich@wtwhmedia.com
of the industry. Ensenso C provides the crucial basis for
data generation and exceeds the requirements of many
applications.
“The high projector power and large sensor
resolutions are particularly advantageous in the
PLANETARY
field of intralogistics,” said Lukas Neumann, Product
Management, VMT. “Here, high-precision components
have to be gripped om a great distance with a large
Brushless DC Gearmotors
measuring volume.”
For other stacking or bin-picking applications in
classic logistics, he could imagine a similar camera with
high projector power but lower resolution and fast High Performance. Zero Maintenance.
recording.
So nothing stands in the way of further
developments and automation solutions in conjunction
with "seeing" robots. RR
Supported by a
high-intensity
projector, the
Ensenso C projects
high-contrast
textures onto the
object to be imaged
| IDS Imaging
RATED SPEED TORQUE GEAR RATIOS VOLTAGES

15 to 658 rpm 11 to 226 lb-in. 4:1 to 162:1 24, 130 VDC
Get more torque, maintenance-free

performance, and high efficiency with
our brushless DC planetary gearmotors.
Metric and US models in stock. New
encoder shaft kit option now available.
bodine-electric.com
THE ROBOT REPORT November 2023 37 info@bodine-electric.com | 773.478.3515 (USA)

Sensors
How computer vision increases

PRODUCTIVITY & SUSTAINABILITY
in agriculture
Integrating computer
vision and other advanced
Computer vision is extending
human senses. Whether
it is allowing cars to drive themselves,
about an acre. Now multiply that field
by about 4,000, and you'll understand
the enormous task farmers take on when
technologies like sensors, automating production lines for safety planting and harvesting thousands of
and efficiency, or allowing us to unlock our acres. A farm of this size can have more
robotics, and AI will result phones with our faces, computer vision can than 750 million plants, each experiencing
in more efficient and more help make human work more productive
and accurate.
microenvironments and conditions that
govern their success.
automated machines that For centuries, farmers have used their With so much land to keep track of,
can treat every single
senses to understand and work the land to farmers need technology to help them
grow the crops we depend on. But today, understand what's happening at critical
plant at a micro level. farmers must extend their senses even junctions. That’s where computer vision
further to provide the food, fuel, and fiber comes into play.
needed for a growing population that is
JORGE HERAUD
expected to exceed 10 billion by 2050, Helping farmers see beyond
VP OF AUTOMATION & AUTONOMY
increasing global food demand by 50%. the tractor cab
JOHN DEERE Adding to the challenge, less than 2% of Computer vision helps farmers "see" crops
the U.S. population works in agriculture, in ways the human eye can’t. It allows
and overall employment of agricultural farmers to manage their limited time and
workers is projected to grow just by 1% resources — like fertilizer, herbicides, and
om 2019 to 2029. This means farmers seeds — and gives them data and insights
have less help and more work to do in the to make timely, accurate decisions for a
coming years. healthier, more successful crop. This helps
Imagine taking care of an entire farmers be more productive, profitable,
football field worth of plants — that is and sustainable.
For example, the human eye can’t
A John Deere tractor distinguish a weed om a crop while
equipped with a
sprayer boom on
each side of the
tractor working in
the field.
| John Deere

The John Deere
8R Autonomous
Tractor was
launched in 2022.
| John Deere
A solution
Y for every
challenge.
driving a tractor 15 miles per hour over images om the cameras to determine if
a field. But a sprayer equipped with the tractor has a clear path forward. This
computer vision can. Using cameras, allows the machine to operate in the field
onboard processors, and millions of autonomously and lets farmers essentially
training images, a technologically advanced be in two places at once. They can set up doosanrobotics.com
sprayer can determine if a plant it sees a tractor to perform a simple, routine task
in the field is a weed or crop and, in in a field while they manage more complex
milliseconds, spray only on the weed with aspects of their operations elsewhere.
herbicide, generating significant cost Computer vision also gives farmers a
savings for farmers and increasing the constant stream of data to inform real-
sustainability of their operations. time decision making. When combined
Computer vision also helps farmers with historical data om previous seasons,
see deep inside machines as they perform farmers can identi the strategies that
precise tasks, like harvesting crops at the produce the best crop and potential areas
end of a season. They use large machines for improvement. This data takes the
that are like factories on wheels to do guesswork out of farming. Farmers only get
several things at once. For example, when one chance each year to produce the best
harvesting corn, the machine will cut possible harvest, and computer vision-
the stalk om the ground, separate the enabled machines and the data they
ear of corn om the stalk, and remove collect are key to making farming more
the individual kernels om the ear. The productive to feed, fuel, and clothe our
machine then transfers the kernels to a growing population.
large cart that takes the crop om the
field to storage. If one of these steps isn’t Creating a path to a better tomorrow
operating at peak performance, it could while feeding the world today
reduce the total crop and profits for But it’s about more than just productivity.
the year. Farmers are stewards of the land. Their
With computer vision, farmers can livelihood depends on it. Our planet’s
monitor and automatically adjust each of health depends on it. Integrating computer
these crucial steps to minimize the time it vision and other advanced technologies
takes to complete the task and ensure the like sensors, robotics, and AI will result
best possible crop harvest in all conditions. in more efficient and more automated
machines that can treat every single plant
Enabling farmers to do more with data at a micro level, ultimately resulting in
In addition to helping farmers see more, more sustainable farming operations.
computer vision also helps farmers do Computer vision is unlocking the
more. Thanks to advanced cameras, fully autonomous farm of the future
tractors can use a 360-degree view to and allowing farmers to become more
identi objects and measure distances. productive, profitable, and sustainable. RR
Onboard processing then evaluates the

Sensors
Commercializing
TACTILE SENSORS
for robot dexterity
Addressing practical
issues such as
I recently wrote an opinion piece about
the need for tactile sensing for evolving
robotic dexterity om toddler to adult.
This commentary om Jeremy Fishel,
a reputable voice in tactile sensing and
robotics, inspired me to explore the
usefulness, reliability In the piece, I make a case for designing practical aspects of commercializing
with tactile sensing in mind to be able to tactile sensors for humanoids in greater
and affordability. achieve truly useful humanoid robots that depth; particularly, the issues of usefulness,
can learn new skills in dexterity. reliability and robustness, and affordability.
I received an insightful comment Of course, none of these can be considered
HEBA KHAMIS
when I shared the article on LinkedIn in isolation, and at the center, one must
CO-FOUNDER
that identifies the practical impediments always be thinking of the objective:
CONTACTILE to the uptake of existing tactile sensing dexterity.
technologies in robotics:
“… The [robotics] community has been Usefulness of tactile sensors in robotics
aching for something affordable that is highly dependent on the application
does something useful and reliably for At a foundational level, different
ages. We’ve had amazing features om applications require different sensing
a wide range of tactile sensors, but they features – temporal and spatial resolution,
all miss the barriers in some key way that sensing range and sensitivity, and even the
prevent[s] widespread adoption …” dimensionality of the sensing.
Tactile sensing on the torso and
arms of a humanoid robot may
be required to detect collisions
Contactile’s PapillArray and, possibly, to classi the
sensor is a so, silicone intentions of a person via
array that can measure physical interactions. For
3D deflection, 3D force example, gently pushing
and 3D vibration at each the back of a humanoid
array element. It can may signal that we want
also measure emergent it to move forward. This
properties such as may be achieved with low
torque, incipient slip and spatial resolution and one-
iction dimensional tactile sensing
| Contactile such as pressure sensing.
On the other hand (pun
intended), tactile sensing in the

Say hello to the
palms and fingers of the humanoid robot

H-SERIES:
are required to aid in manipulation. The
ideal tactile sensor for robotic dexterity
The safest cobot on the
is modular with a scalable size (for … The [robotics] marketplace, delivered
customizing the spatial resolution). It has in 4 weeks or less.
high responsiveness and customizable community has been
sampling equency (for tailoring the
temporal resolution) and sensing range, aching for something
and it is multi-dimensional.
Naturally, there will be trade-offs affordable that does
Six-axis articulation
between some of these features. It is
unlikely that high spatial resolution,
something useful and
high temporal resolution, and high
dimensionality can all be achieved
reliably for ages. We’ve Force torque sensors on
each axis
simultaneously. And, if they could, there had amazing features
would be major implications for the PLe CAT 4 Safety Rating
downstream processing required to from a wide range of
make use of the resulting data. This is 1700mm Reach
one aspect of integration complexity tactile sensors, but they
that should also be considered when
determining usefulness. Other aspects of all miss the barriers 25kg Payload
integration complexity to consider include
cable routing, communications, and in some key way that
power supply.
prevent[s] widespread
doosanrobotics.com
Reliability is a must, but robustness can
depend on cost and replaceability
adoption …
Reliability can mean a few different things.
I take it to mean that applying the same
stimulus to a sensor repeatedly will yield Think of affordability om the
the same output. Sensor dri, usually due perspective of the value of the
to temperature (and humidity) changes, problem the sensor solves.
electromagnetic interference, and other Affordability of a sensor is an interesting
electrical interference (e.g., capacitance), metric that must be considered together
can thwart the reliability of a sensor and, with the usefulness of the sensor, as
thus, reduce confidence in the data and well as the value of the problem that the
the usefulness of a sensor overall. sensor solves. The more useful a sensor
Robustness is somewhat related to is, the more one is willing to pay for it.
reliability in that the sensor must be able The affordability of a useful sensor for a
to survive repeated stimuli. The number of robot that is destined for Mars to build
stimuli the sensor is expected to survive scientific outposts is very different to
will depend on the application and the one that will end up in a robot that is
cost and effort associated with replacing sorting packages in a postal facility.
part of or all of the sensor. Affordability is also something that is
For example, in grocery e-commerce more achievable with volume. Some of
fulfillment, a tactile sensor on a bin- the earliest accelerometers (resistance-
picking robot may be subjected to 1,000 bridge-type) were sold in the early
cycles an hour. It might be acceptable to 1930s to only a couple of hundred
replace a consumable part of the sensor customers for $420 U.S.D. each (the
each day/month/year, if it took only a equivalent of $1,827 in U.S. dollars today).
minute/hour/day and cost only a few Today, you can purchase a 3-axis MEMS
cents/dollars/tens of dollars; of course, accelerometer in single unit quantity for
this must be multiplied by the number of less than $1.50, and accelerometers are
tactile sensors that are deployed in any in practically every mobile device out
one solution/facility. there.
23-0922-Doosan_1-3-Ad.indd 1 10/18/23 11:52 AM

S U M M I T & E X P O
D I S C O V E R T H E L AT E S T
A D VA N C E M E N T S I N
Sponsorship opportunities are available for future DeviceTalks and Robotics programs.
For more information, contact Colleen Sepich. 857.260.1360 | csepich@wtwhmedia.com
Robots must be designed with the right the right sensor must be used in the right
sensor for the right purpose at the right place for the right purpose.
price Contactile’s sensors are designed for a
In robotics, tactile sensing for sensing’s purpose – robotic dexterity – and as such Unleash your
sake is the wrong approach – it will the practical issues of usefulness, reliability,
drive up costs, power consumption and and affordability are all but solved. automation potential
processing requirements, and may provide What are roboticists willing to pay
little value in return. Tactile sensing must for a reliable and robust tactile sensor with Doosan Robotics.
be targeted and planned. that measures the exact parameters that
Robotics companies should ask enable a humanoid robot to achieve
Effortless precision,
themselves the following: What is the human-like dexterity? unbeatable efficiency.
purpose of the sensing and what sensors These tactile sensors could be the
can be used to achieve that purpose? difference between a humanoid robot that
It may be possible for the same sensor can learn skills in dexterity like people do,
to be used for multiple purposes across and one that is stuck with toddler-like
several areas of the robot; but if not, then dexterity. RR
doosanrobotics.com
Contactile
said that
if an end
effector
uses its tactile
sensors, the grip
parameters are
determined in real-
time, and an optimal
grip force is applied
dynamically. Pre-
programming the
grip force is no longer
required - just tell the
gripper to grip and the
sensor feedback will
take care of the rest.
| Contactile

Software
Tormach’s open-source,
ROS-based robotics platform
- which includes the control
system, industrial robot
hardware, and full access to all
system parameters - creates
a fast, accessible solution that
brings industrial robotics to
more researchers, developers,
and students.
| ORNL/Jill Hemman
Bridging the gap between

RESEARCH, INDUSTRIAL ROBOTICS
using ROS
STEVE CROWE • EXECUTIVE EDITOR • THE ROBOT REPORT
Tormach created a ROS-

based industrial robotic
The Robot Operating System (ROS) is a powerful open-source platform for robotics
research, but until recently it lacked industrial-quality hardware that is
tightly integrated with the ROS soware stack. Robot equipment manufacturers use
proprietary, closed-source soware and control systems for their manipulators, leaving
manipulator and control researchers with a steep hill to climb in order to use ROS on industrial robots.
system that avoids Addressing this need and advancing the capabilities of the ROS development
community, Tormach has created a ROS-based industrial robotic manipulator
“black box” issues that and control system that avoids “black box” issues that plague modern robotics
can plague modern applications. Additionally, Tormach’s control system, PathPilot, uses Python as the robot
programming language, creating an intuitive programming interface for robot motion
robotics applications. and unleashing the potential of the Python package ecosystem.

High performance
materials with custom
converting options
This open-source, ROS-based robotics • Legal or contractual obligations oen

platform – which includes the control prevent manufacturers om sharing
system, industrial robot hardware, and full proprietary information with external
access to all system parameters – creates parties.
a fast, accessible solution that brings • They may be concerned about
industrial robotics to more researchers, potential liability issues if their
developers, and students. closed-source control systems are
modified by external parties.
The problem with ROS and proprietary • There is little financial incentive for
robot control systems most manufacturers, and in many
Robot control manufacturers are hesitant cases, there is a strong disincentive:
to allow ROS developers to access all the the need to invest in additional
system parameters in their closed-source documentation, training, and
controls for the following reasons: support inastructure to enable Industry solutions:
• They have invested significant researchers to work with their control • Surface protection for (EOAT)
resources into developing and systems effectively.
testing their proprietary control
• Custom PTFE, UHMW or Nylon
systems and don’t want to expose For these reasons, integrations adhesive backed wear strips or
the inner workings of their system to between ROS and commercially available sheets for high impact areas.
external researchers for fear of losing robot hardware are limited. While drivers
• Custom washers for fastening
intellectual property. exist to connect ROS to other industrial
• There are risks associated with robots, their low (10 – 100Hz) bandwidth motion components.
exposing the system parameters to implementations simply drip-feed • Flexible polymer films and
external researchers. Untested usage waypoints to a proprietary, closed-source silicones for soft robotic
may introduce bugs or other issues controller.
that could compromise the safety or As a result, the user may not applications.
reliability of the system. have access to whether or not the • Low minimum prototype die
cutting.
Custom Converting
Custom Roll Slitting
High Speed Sheeting
Adhesive Lamination
Die Cutting
The OpeN-AM experimental platform, installed at the VULCAN instrument,

features a Tormach ZA6 robotic arm that prints layers of molten metal to create
complex shapes. Studying the 3D-printed welds microscopically with beams of
neutrons allows researchers to better understand factors such as stress caused
by heating and cooling. | ORNL/Jill Hemman
Phone (800) 461-4161
www.cshyde.com
Sensors
Meet HAL: The open-source Hardware

Abstraction Layer
The connection between ROS and a robot’s
hardware relies on a hardware abstraction
layer (HAL). HAL evolved out of the open-
source Enhanced Machine Controller (EMC)
project that had its origin 25 years ago at
the National Institute of Standards and
Testing (NIST).
Active development of HAL continues
today via the LinuxCNC and Machinekit
projects because HAL is flexible, 100%
open-source, and is used in thousands of
machines around the world.
HAL consists of modular components
(loadable binary modules) that
communicate with each other by updating,
reading, and writing named pins that
connect via named signals. In some ways,
HAL is like ROS, but there are important
differences:
• Using PREEMPT-RT Linux extensions,
Python, a programming HAL components written in C execute
language that’s been in use for in a 1kHz real-time thread with
decades, makes programming minimum jitter.
a Tormach robot accessible • HAL has many pre-written
for many. The sheer number components designed for low-level
of devices and soware that hardware control (PWM generators,
run on Python means the ZA6 stepper driver step generators, BLDC
has a seemingly countless and three-phase motor controls,
number of integrations that and more.
are possible.
| ORNL/Jill Hemman The Tormach robot bridges the gap
between ROS with the open-source hal_
ros_control component. The combination
of HAL and ROS allows a wealth of robot
data to be exposed to the user. All process
data is accessible via shell commands, data
logger utilities, and a graphical scope. All
information on the EtherCAT bus, including
torque, current, following error, position,
robot adheres to timing, velocity, and code, with configuration, drives can velocity, and more are available at 1 kHz
path accuracy intents. Data like motor also report additional diagnostics like and exposed via HAL to ROS.
torque, current, following error is usually motor/encoder temperatures and error Since HAL is modular and flexible, users
unavailable, and the slow control loop code history. can alter their robot’s HAL configuration
severely limits what researchers can • 10 digital inputs + 12 digital outputs using pre-built HAL components or by
accomplish. (one digital input usable as probe writing new components in C or Python,
input) allowing easy integration with almost any
Motor and drive feedback to ROS • HAL can report RT latency external device or process.
The ROS/HAL hardware and soware stack • Feedback om ROS and MoveIt,
offers feedback that can provide valuable especially Cartesian pose Preconfigured for ROS
control opportunities. Previously, using a commercially available
The ZA6 provides the following: Most of these feedback elements focus robot with ROS required finding and
• Feedback om each joint, standard on only the lower-level control layers. downloading the appropriate driver for the
configuration: position, velocity Higher-level control layers can provide control, a URDF file to describe kinematics;
feedback, torque feedback in SI units, other opportunities, depending on research creating a moveit configuration, choosing
following error, diagnostics-like error needs. one or more planners, IK solvers, and

perhaps finding and bringing solid models programming language led Tormach to • Using Twilio to send text messages
into Rviz. Configuring a new robot for choose Python for its ZA6 robot. The om the robot.
use with ROS is challenging even for Tormach Robot Programming Language • Using ChatGPT and the Python
experienced ROS developers. (TRPL) uses the Python 3 interpreter and OpenAI API to conversationally create
An optimized default ROS configuration works similarly to other common robot robot programs.
for the manipulator, like that provided programming languages, with commands
by Tormach as part of the control, helps for different move types, commands to While the TRPL interpreter simplifies
alleviate many of these issues. The URDF read and set inputs and outputs, and a lot of programming tasks like move
model (unified robot description format) is commands to set and change tool and user commands and offsets, power users who
defined, motion pipelines are configured, ames. are familiar with ROS are able to access the
and trajectory planners and kinematics It is important to note that any Python underlying ROS API directly.
solvers are selected and optimized so that 3 program is a valid robot program. The
the robot is ready to work out of the box. robot’s ability to interpret any Python Suitable for research and education
The robot hardware, user interface, program means that almost any Python The PathPilot user interface makes it easy
and robot programming language are fully package can be imported to help with more to write simple teach-mode programs
documented and supported by Tormach. challenging robot tasks. Examples include: to help students learn the concepts
The robot’s default ROS configuration • Using the csv and http requests they need to be successful in industrial
will be ideal for most applications, saving libraries to upload data files recorded robotics. Unlike other robots designed for
months of configuration time, and it’s also by the robot to a web server. the classroom, the ZA6 teaches industrial
open-ended to allow users to develop their • Using opencv to recognize ArUco robot concepts like user ames, tool
own unique configurations at will. markers for visual servoing and ames, waypoint programming, and
localization. Cartesian-versus-joint angle waypoint
Python: the robot’s programming • Using numpy and kdl to calculate types. Another reason to use the robot as
language forces in cartesian space om the joint a teaching tool is its easy-to-learn user
The lack of an industry-standard robot torque feedback and robot Jacobian. interface. RR
Your partner
for innovative
manufacturing
Superior encoders for position and motion control

With a comprehensive line up of encoder solutions, Renishaw brings the
expertise needed to address your manufacturing challenges. Whether
your application calls for optical, magnetic or laser technology, our
encoders achieve the highest levels of accuracy, durability and reliability.
Powerfully positioned for innovative motion control.
www.renishaw.com/encoders
Renishaw Inc., West Dundee, IL 60118 usa@renishaw.com
© 2023 Renishaw Inc. All rights reserved.
Encoder General Half PageRobotReportWTWH 09_23.indd 1 8/10/23 9:30 PM

Robotics Robotics
UtiliTrak® Compact
Linear Guide: Precision in
Parallel Motion
Maximize efficiency with UtiliTrak®, the
Bishop-Wisecarver®
2104 Martin Way
ultimate solution for running two systems in Pittsburg, CA 94565
parallel. Featuring DualVee® guide wheels and

www.bwc.com
MadeWell® crowned rollers, it ensures precise 925-439-8272
performance even when mounting surfaces
aren’t perfectly parallel. UtiliTrak® compensates
for mounting errors, eliminating the need for
absolute parallelism. The DualVee® guide wheel
plate assembly and vee channel drive the motion
side, while the MadeWell® crowned roller
and open channel side accommodate parallel
misalignment. Choose Bishop-Wisecarver®’s
UtiliTrak®: easy to order, quick to turn around,
and with all the engineering support you need to
complete your project on time.
Canon U.S.A., Inc.

DC brushless Servo Motors
Today’s increasing demands of automation and robotics
in various industries, engineers are challenged to design
unique and innovative machines to differentiate from
their competitors. Within motion control systems, flexible
integration, space saving, and light weight are the key
requirements to design a successful mechanism.
Canon’s new high torque density, compact and lightweight

DC brushless servo motors are superior to enhance innovative Canon U.S.A., Inc.
design. Our custom capabilities engage optimizing your next Motion Control Products
innovative designs. 3300 North First Street
San Jose, CA, 95134
We are committed in proving technological advantages for 408-468-2320

your success. www.usa.canon.com

Robotics Robotics CGI Inc.
Advanced Products for Robotics and Automation
At CGI we serve a wide array of industries including medical, robotics,

aerospace, defense, semiconductor, industrial automation, motion
control, and many others. Our core business is manufacturing
precision motion control solutions.
CGI’s diverse customer base and wide range of applications have

earned us a reputation for quality, reliability, and flexibility. One
of the distinct competitive advantages we are able to provide our
customers is an engineering team that is knowledgeable and easy
to work with. CGI is certified to ISO9001 and ISO13485 quality
management systems. In addition, we are FDA and AS9100 compliant.
Our unique quality control environment is weaved into the fabric of
CGI Inc.
our manufacturing facility. We work daily with customers who demand
3400 Arrowhead Drive
both precision and rapid turnarounds. Carson City, NV 89706
Toll Free: 1.800.568.4327

ISO QUALITY MANAGEMENT SYSTEMS: ISO 9001• ISO 13485 • AS9100 • ITAR Ph: 1.775.882.3422
Fx: 1.775.882.9599
SIX SIGMA AND LEAN PRACTICES
ARE EMBRACED DAILY WITHIN THE CULTURE WWW.CGIMOTION.COM
Low Friction
Material Fabrication
For Industrial
Automation
Low friction polymers are
important for automation
applications as they can reduce
wear and energy consumption,
improve efficiency, and extend
the lifespan of equipment.
PTFE, UHMW, POM, PEEK, Nylon, and Polyimide films are
often used in various components of automated systems,
including insulators, bearing liners, slides, gears, and other
moving parts. CS Hyde supplies various material types,
thicknesses, adhesive options, and specialized converting
capabilities to create material solutions for friction, impact, CS Hyde Company
www.cshyde.com
or abrasion related issues formed in the fast-moving
environment of industrial automation. Common applications 39655 N. IL Rt. 83
Lake Villa, IL 60046
include wear strips, conveyor liners, bumper plates, and wire
and cable wrapping. 800-461-4161

Robotics Robotics DigiKey
www.digikey.com
701 Brooks Avenue South, Thief River

Falls, MN 56701 USA
sales@digikey.com
1-800-344-4539
Omron’s TM Collaborative Robots

Increase production and reduce worker fatigue with Omron Automation’s TM
Collaborative Robots. Repetitive tasks such as pick and place inspection, machine
tending, assembly, and more are easily handled by the 6 axis TM cobot. Utilizing
graphical programming with the TMFlow software, hand guided position recording,
and a built-in vision system, users can set up simple applications in mere minutes.
Omron’s TM Collaborative Robots are ISO 10218-1:2011 and ISO/TS-15066 compliant
and include features like rapid changeover using TMVision and Landmark, advanced
collaborative control, and external camera support.
Harmonic Drive
Servo Grade AMR Propulsion

Drive Trains
The drive wheels on Autonomous Mobile Robot
Platforms benefit from the inherent characteristics
of harmonic planetary technology, primarily,
smoothness of travel, backdrivability, and an
efficiency curve that does not degrade over time.
The integral cross roller bearing construction
contributes to an excellent balance of torque
density, stiffness, and radial load support in a
compact and reliable package. Available in dozens
of standard reduction ratios, these low backlash
drive trains include motor adaptation as required.
42 Dunham Ridge
Beverly, MA 01915
United States
www.harmonicdrive.net

Robotics Robotics
Kona Connectors
60A per contact, High-reliability
Connectors
Kona expands the Harwin High-Reliability
portfolio into new levels of current – 60A
per contact. Designed to withstand testing
environments and conditions.
• 2, 3 or 4 single row configurations
• Vertical cable-to-board or cable-to-cable
• Vibration and shock resistant, compact power
future-proofed
• 60A max per contact
• 6-finger contact design to maintain electrical
contact through high vibration and shock
Other useful features include reverse fix screws, polarization,

and identification of the #1 position. Harwin provides CAD
Models, Test Reports and F.O.C samples to assist you in the
design process.
For more information, visit harwin.com
Rotary encoders from RENCO

The new R35i and R35iL encoders from RENCO
are incremental rotary encoders without integral
bearings. With resolutions of up to 40,000 HEIDENHAIN CORPORATION
measuring steps per revolution, they are particularly 333 East State Parkway
well-suited as feedback systems for stepper motors Schaumburg, IL 60173
in Closed Loop operation and for exact position
measurement in measuring machines such as 847-490-1191
laser scanners. For particularly limited mounting www.heidenhain.us
situations, RENCO offers the R35iL. It is one of the marketing01@heidenhain.com
smallest rotary encoders currently on the market,
with a height of only 8.6 mm.
HEIDENHAIN produces the RENCO rotary encoders,

and also sells them worldwide. This means that
RENCO rotary encoders benefit from HEIDENHAIN’s
comprehensive know-how in the development and
production of encoders. HEIDENHAIN develops
and manufactures linear and angle encoders, rotary
encoders, digital readouts and numerical controls
for demanding positioning tasks.

Robotics Robotics
Easily design a maintenance-
free gantry robot system that
meets all your requirements for
up to 40% less cost
Gantry robots have become a critical

component for manufacturing and
warehouse automation, and igus®
provides turnkey and custom gantry systems that are built
with self-lubricating plastic liners which are engineered
to slide instead of roll, allowing for smoother and quieter
operation vs. traditional recirculating ball bearings.
Every gantry system that igus® offers provides a

lightweight, corrosion-resistant solution that is ideal for
pick and place, sorting, labeling, measuring, inspection, igus, inc.
and repetitive material handling applications. 57 Ferris Ave,
Rumford, RI 02916
Due to their modular nature, igus® gantry robots are easily www.igus.net
customizable, and free onsite consultation is available to
800.521.2747
ensure the perfect solution at the best price possible.
sales@igus.com
Interconnect Solutions
LEMO® is the industry leader in the design and
production of precise custom interconnect systems.
LEMO products are designed and manufactured
according to rigorous and controlled processes.
Inspection and traceability of products are systematically
ensured in compliance with our standards. High-quality
LEMO Push-Pull connectors are used in a wide range of
challenging application environments, such as medical,
test & measurement, research, defense & military,
information systems, aerospace & autonomous vehicles,
robotics, automotive, industrial control, nuclear,
broadcast & audio-video, and communications.
LEMO® has been designing precision connectors

for over seven decades. Offering more than 90,000
LEMO USA, Inc.
combinations of products that continue to grow through 635 Park Ct.
customer-specific designs, LEMO® and its brands Rohnert Park, California 94928
REDEL®, NORTHWIRE®, and COELVER® currently serve
Ph: 707.578.8811
more than 100,000 customers in over 80 countries
E-mail: info_us@lemo.com
around the world. Website: https://www.lemo.com/en

Robotics Robotics
Fully Automate Your Automation
The factory of the future demands higher output with
increased flexibility, and cobots can’t do it alone. The
Cobot Feeder from Applied Cobotics addresses these
demands with high-mix, high-volume production while
eliminating cobot downtime and alleviating staffing
issues. The bottom-line result is increased output without
increased labor.
The Cobot Feeder presents a worktable that adjusts

vertically, synchronizing with each custom tray on the rack
tower. A horizontal loader/unloader provides accurate and
repeatable motion while positioning trays in front of the
cobot. These features, along with the portable dunnage
tray cart, make the Cobot Feeder from Applied Cobotics
an essential complement to any collaborative automation
system. With a 90-day ROI, small
to medium-sized enterprises PBC Linear
will quickly achieve lights-out 6402 E. Rockton Road
Roscoe, Illinois 61073 USA
manufacturing, increasing safety,
quality—and profits. +1.815.389.5600
pbclinear.com
SmartRunner Explorer
3-D for Robotic Gripping
Enter the third dimension
of automation at the
speed of light—the
SmartRunner Explorer
3-D generates high-
precision 3-D point cloud
images in addition to 2-D
images. It is optionally
available with stereo vision
technology or time-of-
flight (ToF) technology.
• Laser class 1 for eye safety Pepperl+Fuchs, Inc.

• Operating frequency up to 30 Hz 1600 Enterprise Parkway
• Gigabit Ethernet TCP/IP interface Twinsburg, Ohio 44087 USA
• Compact dimensions (165 x 67 x 56 mm)
Phone: 330-486-0002
• Supression of ambient light > 100 klx
www.pepperl-fuchs.com
• Raw image size 640 x 480 pixels
sales@us.pepperl-fuchs.com
• Universal ROS drivers

Robotics Robotics
Meet POSITAL’s Next Generation
Position and Motion Sensors!
POSITAL has launched a major upgrade to its IXARC

rotary encoders, kit encoders and TILTIX inclinometers.
Introduced as part of POSITAL’s NEXTGEN initiative,
the upgrades include new TMR magnetic sensors
for encoders, new MEMS accelerometer packages for
inclinometers, and updated microprocessors for most
products. There is also a new in-house developed ASIC
and new Wiegand sensors that support zero-maintenance,
battery-free operation of multiturn encoders. These changes
deliver improvements to precision and energy efficiency, while
maintaining mechanical and electrical compatibility with
earlier products.
More NeXtGen product announcements POSITAL Inc.

are on the way. Stay tuned! 1 N. Johnston Ave. Suite C238
Hamilton, NJ 08609 USA
For more information, please visit:
www.posital.com
Tel: 609-750-8705
info@fraba.com
An encoder series designed for

use in harsh environments
Renishaw’s FORTiS™ delivers superior

repeatability, reduced hysteresis, and improved
measurement performance due to an innovative
non-contact mechanical design that does
not require a mechanical guidance carriage. It
provides high resistance to the ingress of liquids
and solid debris contaminants. It features an
extruded enclosure with longitudinally attached
interlocking lip seals and sealed end caps. The
readhead body is joined to a sealed optical unit by a blade, which travels through
the lip seals along the length of the encoder. Linear axis movement causes the
readhead and optics to traverse the encoder’s absolute scale (which is fixed to
the inside of the enclosure), without mechanical contact.
Renishaw, Inc.
1001 Wesemann Dr.
West Dundee, IL, 60118
Phone: 847-286-9953
email: usa@renishaw.com
website: www.renishaw.com

Robotics Robotics Ruland Manufacturing
Zero-Backlash Couplings for Robotic Systems
Ruland Manufacturing offers a variety of zero-backlash servo

couplings designed for use in high precision applications like
automation and robotics. Ruland offers beam, bellows, disc,
oldham, jaw, and newly-released Controlflex couplings in
thousands of off-the-shelf combinations and sizes to help
designers optimize their systems.
Robotic vision systems, material handling robots, and

automated guided vehicles have infamously strict requirements
that require engineers to balance torque, weight, dampening,
and more, all while retaining extremely precise power
transmission. Ruland servo couplings excel in demanding
applications and can be selected based on a wide variety of
performance characteristics.
Ruland Manufacturing
Visit Ruland.com for access to everything you need to make a 6 Hayes Memorial Dr.
coupling design decision including: full technical product data, Marlborough, MA 01752
3D CAD models, installation videos, and eCommerce to make
508-485-1000
prototyping easy.
www.ruland.com
email: sales@ruland.com
Compact, rugged motion

sensing for any task
Silicon Sensing’s gyroscopes, accelerometers and inertial

systems offer precise, compact and affordable solutions
for robotics applications, in any environment.
Our products include:

• DMU11 - a low cost, compact, precise, six-degrees-
of-freedom (6-DOF) device delivering market-
leading performance that is calibrated over its full
rated temperature range.
• PinPoint® - A tiny gyro measuring only 5mm x
6mm and delivering on performance, reliability and
price. Available in both flat and orthogonal mounts. Silicon Sensing
Clittaford Road
• CMS300 - a robust, compact gyro and dual-axis Southway
accelerometer delivering precise performance with Plymouth
Devon
low power consumption. Available in both flat and
PL6 6DE
orthogonal mount packages. England
Telephone: 01752 723330

Inertial sensing for any task. www.siliconsensing.com/products

Ad Index
Advanced Navigation ..........................................................23
Bishop Wisecarver ......................................................... 33,48
Bodine Electric Company .............................................35,37
SALES
11 • 2023 therobotreport.com
Ryan Ashdown
LEADERSHIP TEAM
Publisher
rashdown@wtwhmedia.com Mike Emich
Boker’s ..........................................................................................18 216.316.6691 memich@wtwhmedia.com
508.446.1823
Canon U.S.A. Inc..................................................................11,48 Jami Brownlee @wtwh_memich
jbrownlee@wtwhmedia.com
CGI Inc. .................................................................................49,BC
224.760.1055 CEO
Chieftek Precision .................................................................27 Scott McCafferty
Mary Ann Cooke smccafferty@wtwhmedia.com
CS Hyde Company .......................................................... 45,49 mcooke@wtwhmedia.com 310.279.3844
781.710.4659 @SMMcCafferty
DigiKey Electronics ...........................................................3,50
Jim Dempsey EVP
DOOSAN Robotics Americas ................................ 39,41,43 jdempsey@wtwhmedia.com Marshall Matheson
216.387.1916 mmatheson@wtwhmedia.com
Harmonic Drive .................................................................... 1,50 805.895.3609
Mike Francesconi @mmatheson
Harwin .................................................................................... 17,51 mfrancesconi@wtwhmedia.com
630.488.9029 CFO
HEIDENHAIN CORPORATION ......................................... 5,51 Ken Gradman
igus .........................................................................................21,52 Jim Powers kgradman@wtwhmedia.com
jpowers@wtwhmedia.com 773-680-5955
LEMO USA ........................................................................52,IBC 312.925.7793
@jpowers_media
Parvalux, a maxon company .......................................cover
Courtney Nagle
PBC .........................................................................................13,53 cseel@wtwhmedia.com
440.523.1685
Pepperl + Fuchs .............................................................. 25,53 @wtwh_CSeel
POSITAL .............................................................................. 29,54

Renishaw ............................................................................47,54
Ruland Manufacturing ......................................................7,55
SICK, Inc. ...................................................................................... 4
SIKO ..............................................................................................12 FOLLOW THE WHOLE TEAM
Silicon Sensing Systems ................................................9,55
Stow Robotics ....................................................................... IFC
@DESIGNWORLD

Learn More
Scan QR Code!
LEMO Robotic Connectors

These connectors deliver exceptional performance in harsh
environments, ensuring long-lasting durability. Whether in
industrial automation, medical robotics, or for Rovers and
Legged Robots, LEMO connectors provide the ability to connect
sensors, actuators, and control systems seamlessly.
• Light weight • Compact

• Durable • Ergonomic
YOUR CUSTOM SOLUTIONS ARE
CGI STANDARD PRODUCTS
Advanced Products for Robotics and Automation

CGI Motion standard products are designed with customization
in mind. Our team of experts will work with you on selecting the
optimal base product and craft a unique solution to help differentiate
your product or application. So when you think customization, think
standard CGI assemblies.
Connect with us today to explore what CGI Motion can do for you.
copyright©2021 cgi inc. all rights reserved.
800.568.GEAR (4327) • www.cgimotion.com

Design World Robotics Handbook 11 2023

Uploaded by

Document Information

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Design World Robotics Handbook 11 2023

Uploaded by

Copyright:

Available Formats

www.designworldonline.

High Efﬁciency Easy Mounting to a Wide Variety

Harmonic Drive LLC | 42 Dunham Ridge | Beverly, MA 01915 | 800.921.3332 | www.HarmonicDrive.net

DW 9x10.875 HPG Ad.indd 1 10/25/23 10:14 AM

Apptronik’s Apollo humanoid

COLLABORATIVE ROBOTICS SENSORS

DESIGN & DEVELOPMENT

2 November 2023 www.therobotreport.com THE ROBOT REPORT

AI-based code reading is just minutes away.

Lector One Box is a registered trademark of SICK Sensor Intelligence WWW.SICK.COM

guides on the Design World Art Director

design-guide-library Mariel Evans

6 November 2023 www.therobotreport.com THE ROBOT REPORT

Ruland Manufacturing is proud to

• Zero-backlash jaw couplings for vibration dampening

VIBRATION ISOLATING COMPONENTS QUICK CLAMPING COLLARS

Welding cobot delivers

8 November 2023 www.therobotreport.com THE ROBOT REPORT

From 2 to 20 inches per minute

THE ROBOT REPORT November 2023 9

ROI: one order paid off the cobot

10 November 2023 www.therobotreport.com THE ROBOT REPORT

Troubleshooting in real time Future applications

Contact us for custom specific solutions

The biggest issue that this machine is solving is cobot downtime.

The Cobot Feeder is easy to install, operate, and can be purchased

Apollo stands 5 feet 8

14 November 2023 www.therobotreport.com THE ROBOT REPORT

THE ROBOT REPORT STAFF What are the origins of Apptronik?

THE ROBOT REPORT www.therobotreport.com November 2023 15

16 November 2023 www.therobotreport.com THE ROBOT REPORT

Why are so many companies now

THE ROBOT REPORT www.therobotreport.com November 2023 17

humanoid really is. In the early days of computers, you

What are the features and capabilities of Apollo?

18 November 2023 THE ROBOT REPORT

THE ROBOT REPORT www.therobotreport.com November 2023 19

20 November 2023 www.therobotreport.com THE ROBOT REPORT

FLEXIBILITY FOR DYNAMIC APPLICATIONS

DESIGNED TO PREVENT CORKSCREWING

NO MINIMUM LENGTH REQUIREMENT

UL-VERIFIED GUARANTEE UP TO 36 MOS.

Meets 20+ manufacturer standards

CLOUD GROUND CONTROL

Scan the QR code or visit

Teaching robots new tricks

A new AI agent developed by NVIDIA

24 November 2023 www.therobotreport.com THE ROBOT REPORT

Pick and place applications require special

author of the Eureka paper. “Eureka is

26 November 2023 www.therobotreport.com THE ROBOT REPORT

Using its Generative

28 November 2023 www.therobotreport.com THE ROBOT REPORT

Muliturn absolute models feature

More NEXTGEN product

THE ROBOT REPORT www.therobotreport.com November 2023 29

Humanoids offer the

30 November 2023 www.therobotreport.com THE ROBOT REPORT

THE ROBOT REPORT www.therobotreport.com November 2023 31

VMT is now using a robot

32 November 2023 www.therobotreport.com THE ROBOT REPORT

ROBOT TRANSFER UNITS BUILT ON

Application Four Ensenso C

34 November 2023 www.therobotreport.com THE ROBOT REPORT

This open-source, ROS-based robotics • Legal or contractual obligations oen