DARPA Robotics Challenge Proposers’ Day

April 16, 2012

DARPA Robotics Challenge Proposers’ Day

The Proposers’ Day will begin at 12:10 PM EDT
April 16, 2012

2

DARPA Robotics Challenge Proposers’ Day

Dr. Gill Pratt
Program Manager, DARPA

3

DARPA Robotics Challenge Proposers’ Day Agenda

12:00PM-12:10PM 12:10PM-12:15PM

Set up/Test Connection Introductory Remarks, OSTP Dr. John Holdren, Assistant to the President for Science and Technology and Director of Science and Technology Policy (OSTP) Dr. Kaigham J. Gabriel, Acting Director, DARPA Mr. Paul Eremenko, Director, DARPA TTO Acting Director/Deputy

12:15PM-12:25PM 12:25PM-12:40PM 12:40PM-1:40PM 1:40PM-1:55PM 1:55PM-2:10PM 2:10PM-2:25PM 2:25PM-2:45PM 2:45PM-3:15PM 3:15PM

Introductory Remarks, DARPA DARPA/TTO Overview Robotics Challenge Overview Contracts Management GFE Hardware GFE Software Break Q/A Response Adjourn

Dr. Gill Pratt, Program Manager, DARPA Mr. Chris Glista, Contracting Officer, DARPA Dr. Robert Playter, Boston Dynamics, Inc. Mr. Nate Koenig, Foundation, Inc. Open Source Robotics

4

OSTP Dr. Office of Science and Technology Policy (OSTP) 5 .Introductory Remarks. John Holdren Assistant to the President for Science and Technology and Director.

John Holdren VIDEO 4/16/2012 Further dissemination only as directed by DARPA Public Release Center or higher DoD authority.Dr. 6 .

DARPA 7 .Introductory Remarks. Gabriel Acting Director. Kaigham J. DARPA Dr.

Kaigham J. 8 .Dr. Gabriel VIDEO 4/16/2012 Further dissemination only as directed by DARPA Public Release Center or higher DoD authority.

Paul Eremenko. 9 . Acting Director Tactical Technology Office Briefing prepared for Robotics Challenge Proposers’ Day April 16. Distribution Unlimited). 2012 Photo: DARPA 4/16/2012 Distribution Statement “A” (Approved for Public Release.DARPA/TTO Overview Mr.

Eisenhower 4/16/2012 Distribution Statement “A” (Approved for Public Release. Coined the term “military-industrial complex” and warned against its unwarranted influence. 34th President of the United States 1953-1961. 10 . Distribution Unlimited). The satellite was not a threat.DARPA 1 9 5 7 1 9 5 8 First orbiting satellite. Sputnik Dwight D. but the level of technology indicated that the Soviet Union possessed superior capability for intercontinental reconnaissance and bombing. Created DARPA in response to Sputnik.

As the DoD’s primary innovation engine.S. adversaries by maintaining the technological superiority of the U. national security and create strategic surprise for U. Distribution Unlimited). the Agency relies on diverse performers to apply multi-disciplinary approaches to both advance knowledge through basic research and create innovative technologies that address current practical problems through applied research. military.S.S. DARPA undertakes projects that are finite in duration but that create lasting revolutionary change. 11 .Mission The Defense Advanced Research Projects Agency (DARPA) was established in 1958 to prevent strategic surprise from negatively impacting U. To fulfill its mission. 4/16/2012 Distribution Statement “A” (Approved for Public Release.

Idea leadership culture ► Create and prevent strategic surprise ► Lean. agile risk-taking organization ► Idea-driven and outcome-oriented ► Demonstrate solution concepts 4/16/2012 Distribution Statement “A” (Approved for Public Release. 12 . Distribution Unlimited).

13 . Distribution Unlimited).“Impossible” ideas become real life at DARPA 4/16/2012 Distribution Statement “A” (Approved for Public Release.

net 4/16/2012 Distribution Statement “A” (Approved for Public Release. Distribution Unlimited).Spaceflight 1 8 6 5 1 9 5 7 1 9 6 7 Books DARPA: F1 engine Saturn V Photo: http://moonbooks. 14 .

Wireless communications 1 9 6 6 1 9 8 0 ’ s 1 9 8 6 Television DARPA: research Cellular phone Photo: http://www. 15 .globalnerdy. Distribution Unlimited).com 4/16/2012 Distribution Statement “A” (Approved for Public Release.wired.com Photo: http://www.

News and personal communication available on tablet devices.The internet 1 9 6 9 1 9 6 9 2 0 1 0 Fictional access news and personal communication on tablet devices.mercurybrief. Distribution Unlimited). Original ARPAnet for remotely sharing large volumes of data.com/ 2010/01/kubrick-slates-tablets-2001-film/ Photo: http://www. Photo: http://www. 16 .surfmobee.com 4/16/2012 Distribution Statement “A” (Approved for Public Release.

17 .“Stealth” 1 9 7 6 1 9 7 8 1 9 9 1 “Hopeless diamond” concept rejected by U. Distribution Unlimited).S. Air Force DARPA sponsored flight technology demonstrator to improve survivability of a single aircraft against a modern IADS Combined with precise weapons against C2 targets to improve survivability for all forces in Desert Storm 4/16/2012 Distribution Statement “A” (Approved for Public Release.

18 . Distribution Unlimited).Global Positioning System 1 9 6 3 1 9 9 0 ’ s 2 0 1 0 DARPA Transit 2A satellite pioneered doppler navigation for specific military missions. Continued military and commercial refinement for tactical applications 4/16/2012 Distribution Statement “A” (Approved for Public Release. Became global precision navigation technology for military and civilian use.

Surveillance UAV’s 1 9 8 6 1 9 9 7 2 0 0 9 DARPA flight technology demonstrator to prove the feasibility of the technology. shelved because it did not fit into prevailing air operations thinking. Photo: General Atomics Photo: General Atomics 4/16/2012 Distribution Statement “A” (Approved for Public Release. Rapidly adopted and matured to counter new threats more effectively than existing platforms and doctrine could. 19 . Distribution Unlimited).

Distribution Unlimited). 20 .html 4/16/2012 Distribution Statement “A” (Approved for Public Release.jeffbots.com/maria.Automation 1 9 2 7 2 0 1 1 2 0 X X Movies DARPA: Autonomous Robotics Manipulation Image: http://www.

Multi-mode mobility 1 9 6 2 2 0 1 0 2 0 X X Books Research Image: http://www.tomswift.info 4/16/2012 Distribution Statement “A” (Approved for Public Release. Distribution Unlimited). 21 .

22 . Distribution Unlimited).Continuous accomplishment Space Launch and Navigation The Internet RF Stealth Synthetic Aperture Radar GPS Autonomous Systems “X”-Planes 4/16/2012 Distribution Statement “A” (Approved for Public Release.

Organization AEO Adaptive Execution Office • Agile Programs with Frequent Development Cycles • Conduct Systematic Rigorous • Assessments • Explore New Contracting Approaches • Develop Strong Relationships DSO Defense Sciences Office • Physical Sciences • Materials • Mathematics • Training & Human Effectiveness • Biological Warfare Defense • Biology I2O Information Innovation Office • Global ISR • Cyber • Social Networks • Computational Social Science MTO Microsystems Technology Office • Basic Science Core • Devices • Integration • Power • Architectures STO Strategic Technology Office • Comms & Networks • Global Tactical ISR • Energy • Hybrid Warfare • TTO Tactical Technology Office • Space Systems & Space Awareness • Hypersonics • Space Access • Aero.& Hydrodynamic Systems • Ground & Soldier Systems • Design Synthesis • Manufacturing • Qualification/V&V • Autonomy • Language Transparency • Edge Finding • Training/ Education • Application • Extreme Environments 4/16/2012 Distribution Statement “A” (Approved for Public Release. 23 . Distribution Unlimited).

Professional reach Flat organization Little hierarchy to ensure the free and rapid flow of information. No DARPA labs Majority of the research is sponsored in industry and universities with a small amount in government labs. Project-based assignments Projects organized around a challenge model and typically last three to five years. and decisions. independent people with big ideas and empowers them. Flexible outsourcing of staff and performers Great talents and ideas from industry. ideas. Outstanding program managers DARPA hires creative. 4/16/2012 Distribution Statement “A” (Approved for Public Release. Distribution Unlimited). and administrative services from other commercial and government agencies. longer if necessary to facilitate transition. 24 . contracting. universities. and government labs with technical.

mil 4/16/2012 Distribution Statement “A” (Approved for Public Release. Distribution Unlimited). 25 .darpa.www.

Gill A. Pratt.DARPA Robotics Challenge Proposer’s Day April 16th. Distribution Unlimited) 26 . 2012 Dr. Program Manager Distribution Statement "A" (Approved for Public Release.

2011 27 .2005 Deepwater Horizon 2010 Distribution Statement "A" (Approved for Public Release. Distribution Unlimited) Fukushima .Recent Disasters Katrina .

3. 28 Distribution Statement "A" (Approved for Public Release. and important DoD capability for HADR (Humanitarian Assistance and Disaster Relief) missions 2. March 1960 Target disaster response in dangerous environments.” IEEE Spectrum. C. and energetic efficiency. before the cascade of failures carried reactor 1 beyond any hope of salvation. 4. R. operator-interactive simulator. Licklider (head of DARPA IPTO 1962) IRE Transactions on Human Factors in Electronics. reveals clear inflection points where minor differences would have prevented events from spiraling out of control. Distribution Unlimited) . Welcome a wide range of international contributors including traditional and nontraditional DARPA performers from a variety of fields. Man-Computer Symbiosis J. volume HFE-1. Fukushima . pages 4-11. real-time. mobility. 36. Advance supervised autonomy. Catalyze the robotics industry by developing a validated.2011 “… close study of the disaster’s first 24 hours. manipulation. November 2011 pg.Inspiration and Goals 1.

Human-like robot capabilities are easier for domain experts to understand and untrained operators to control Distribution Statement "A" (Approved for Public Release. Environment. from hand tools to vehicles 3. No shortage of human tools.Why emphasize human-like robot capabilities? 1. Distribution Unlimited) 29 . even degraded. has been engineered for humans 2.

Distribution Unlimited) . Auto Robot Sprv. Auto Robot Environment Decouple Predictive Model Environment DARPA Challenge 30 Distribution Statement "A" (Approved for Public Release.Supervisory Autonomy and Predictive Models High Fidelity Interface Low Fidelity Interface Variable Fidelity Interface Human Human Environment Environment Environment Human Human Human Human Predictive Model Decouple Tele-op Robot Tele-op Robot Predictive Model Environment Predictive Model Sprv.

Questions this Program will Address 4. energetics Distribution Statement "A" (Approved for Public Release. Auto Robot 1. What kind of I/O 2. What kind of messages 3. manipulation. Tasks and Metrics Human Predictive Model Sprv. mobility. Distribution Unlimited) 31 . What autonomy.

Example Disaster Challenge Scenario Capabilities Autonomy – Decision-making Autonomy .Perception Dismounted Mobility Mounted Mobility Dexterity 1. Replace component X X X Distribution Statement "A" (Approved for Public Release. Locate and close valve near leaking pipe 8. Travel dismounted across rubble 3. Distribution Unlimited) Strength Endurance . Drive utility vehicle to site 2. traverse industrial walkway 6. Remove debris blocking entryway 4. Climb industrial ladder. Open door. Use tool to break through concrete panel 7. enter building X X X X X X X X X X X X X X X X X X X X X X X X X X 32 X X X X Tasks 5.

with some loose soil and rocks. and ignition.Drive a utility vehicle to the site The robot must demonstrate mounted mobility by ingress to the vehicle. The object will have size.Remove debris blocking an entryway The robot must demonstrate the dexterity and strength to move an object blocking an entryway. Task 2 -Travel dismounted across rubble The robot must demonstrate dismounted mobility by crossing terrain ranging from smooth and level. The object mass is expected not to exceed 5 kg. including steering. Task 4 . The robot must steer. The robot must also demonstrate manipulation by operating the controls. and other properties to be movable either by a person or by the GFE Platform. and egress from the vehicle. brakes. Distribution Unlimited) .Open a door and enter a building The robot must demonstrate the dexterity to operate a door handle and the strength to push the door open.Planned Tasks – subject to change Task 1 . and brake. to rough and sloped. weight. throttle. 33 Distribution Statement "A" (Approved for Public Release. Task 3 . driving it on a road. This terrain will be easily traversable by a human. accelerate.

and the manipulation ability to close the valve Task 8 . and the bi-manual manipulation ability to extract and replace the pump. the manipulation ability to loosen one or more fasteners. Distribution Unlimited) 34 . Task 7 . The power tool is expected to be an air or electric impact hammer and chisel. Distribution Statement "A" (Approved for Public Release.Replace cooling pump The robot must demonstrate the perception ability to locate the pump.Locate and close valve near leaking pipe The robot must demonstrate the perception ability to find a leaking pipe and a nearby valve. Task 6 .Climb an industrial ladder and traverse an industrial walkway The robot must demonstrate dismounted mobility to traverse an industrial elevated walkway. or an electric reciprocating saw.) – subject to change Task 5 . It is expected that the walkway (or catwalk) will have a grated surface and handrails.Use a tool to break through a concrete panel The robot must demonstrate using a power tool to perform forceful manipulation.Planned Tasks (cont. the dismounted mobility to approach the valve.

Funded Teams design and build platform systems to participate in Disaster Response Challenge. Distribution Unlimited) 35 .Participation Options Track A . Disaster Virtual Challenge conducted to identify which teams will be provided GFE Robot and additional funding to participate in Disaster Response Challenge Track C – Unfunded teams use Simulator to and develop algorithms and participate in Disaster Virtual Challenge and will compete along with Track B teams for GFE Robot and funding award Track D – Unfunded teams develop platforms to compete in Disaster Response Challenges Distribution Statement "A" (Approved for Public Release. Track B –– Teams develop algorithms using DARPA provided Simulator.

Planned Schedule and Funding Distribution Statement "A" (Approved for Public Release. Distribution Unlimited) 36 .

with up to twelve (12) teams. Track B/Track C: last six (6) months after the Virtual Disaster Response Challenge: Up to $750k additional for each team.Planned Program Funding The program has planned the following funding for teams. Distribution Unlimited) 37 . Prize Anticipated to be $2M to a single team. Phase 2 Up to $1M for up to eight (8) of the top performing teams from the first physical disaster challenge. Distribution Statement "A" (Approved for Public Release. Track B: first nine (9) months through the Virtual Disaster Response Challenge: Up to $375k for each team. Phase 1 Track A: Up to $3M for each team (up to five (5) teams for fifteen (15) months). with up to six (6) teams. This plan is subject to change depending on the number of qualified teams and available resources.

Distribution Unlimited) 38 .Planned Key Dates • May 31. 2012 – BAA Closing • October 2012 – Anticipated Contract Awards/Program Kickoff • June 2013 – Virtual Disaster Response Challenge • December 2013 – Disaster Response Challenge #1 • December 2014 – Disaster Response Challenge #2 Distribution Statement "A" (Approved for Public Release.

Distribution Unlimited) 39 .darpa.mil Distribution Statement "A" (Approved for Public Release.www.

Chris Glista DARPA Contracts Management Office DARPA Robotics Challenge Proposers’ Day April 16.BAA Process Mr. 2012 Distribution Statement A 40 .

• ALL questions to DARPA-BAA-12-39@darpa.mil 4/16/12 Distribution Statement A 41 .BAA Specifics • BAA and any amendments posted in FEDBIZOPPS • BAA covers all info needed to propose • TIME PERIOD – BAA is open until May 31. 2012 • Instructions are detailed in the BAA (Follow closely) • Following the proposal instructions assists the evaluation team to clearly understand what is being proposed and supports a timely negotiation.

mil • “A general announcement of an agency’s research interest including criteria for selecting proposals of all offerors capable of satisfying the Government’s needs. 4/16/12 Distribution Statement A 42 .af.hill.” • For the acquisition of basic and applied research not related to the development of a specific system or hardware procurement.BAA Background • Federal Acquisition Regulation (FAR) Part 35 http://farsite.

BAA Background (cont. and fund availability. • Primary basis for selecting proposals shall be technical.) • Used when proposals with varying technical and scientific approaches can be expected • Proposals need not be evaluated against one another since they are not submitted in accordance with a common work statement. • Cost realism shall also be considered 4/16/12 Distribution Statement A 43 . importance to agency programs.

) • Contractors SHALL NOT subcontract technical or scientific work without the contracting officer’s knowledge 4/16/12 Distribution Statement A 44 .BAA Background (cont.

IMPLICATIONS • FAR PART 15 “Contracting By Negotiation” does not apply in full • No “competitive range” determination • No mandatory “discussions” • No opportunity for proposal revision • “Cost and Pricing Data” (certification required for all FAR-based contract proposals greater than $700K) • Subcontract consent and key personnel clauses to be included in awards 4/16/12 Distribution Statement A 45 .

Communications • ALL questions to DARPA-BAA-12-39@darpa. or cost estimate • Informal feedback may be provided once selection(s) are made – no “ranking” provided 4/16/12 Distribution Statement A 46 . solution.mil • After Receipt of Proposals – Government (PM/PCO) may communicate with proposers to understand the meaning of some aspect of the proposal that is not clear or to obtain confirmation or substantiation of a proposed approach.

etc. Teaming Not Required 4/16/12 Distribution Statement A 47 . Export Laws.Applicant Eligibility • All interested/qualified sources may respond • International participants/resources may participate to the extent authorized by applicable Security Regulations. • Small Business Participation Encouraged.

) • Government agencies/labs.Applicant Eligibility (cont. contractual authority) establishing their eligibility to propose to government solicitations 4/16/12 Distribution Statement A 48 . FFRDCs cannot propose to this BAA in any capacity. UNLESS they can clearly demonstrate the work is not otherwise available from the private sector AND they also provide written documentation citing the specific statutory authority (as well as. where relevant.

Organizational Conflict of Interest • All facts relative to a potential conflict of interest must be disclosed.505 • Provided Systems Engineering and Technical Direction • Contractors MAY NOT simultaneously provide SETA support and be a technical performer at DARPA without waiver approved by DARPA Director 4/16/12 Distribution Statement A 49 . • Examples of conflicts listed at FAR Part 9.

af.acq.hill.Award Type Award Instrument • Contract. Grant. Cooperative Agreement.mil/whs/directives/corres/html/321006r. Cooperative Agreements) • www.dtic.htm (Grants. Other Transaction • http://farsite.osd.doc (Other Transactions) • In all cases the Contracting Officer shall have sole discretion to select award type instrument 4/16/12 Distribution Statement 50 .mil/ (FAR Contracts) • http://www.mil/dpap/Docs/otguide.

Rights to Technical Data and Computer Software • Assert rights to all technical data & computer software generated. developed. and/or delivered to which the Government will receive less than Unlimited Rights • Assertions apply to Prime and Subs • Justify “Basis of Assertion” • Use defined “Basis of Assertion” and “Rights Category” • Assessed during evaluation under the “Potential to Accomplish Technology Transition” Evaluation Factor 4/16/12 Distribution Statement A 51 .

Atlas Robot Overview for DARPA Robotics Challenge
Robert Playter Marc Raibert
April 16, 2012

Atlas Overview • Near copy of PETMAN/Atlas • 50th percentile male anthropometry • 27 actuated, hydraulic DOF’s • 2 on-board computers • Power tether • Sensing head • Modular wrist • Protective shells

Current Performance

PETMAN Video

Robot Degrees of Freedom (DOF)
• 27 Active DOFs
– – – – – – – – NECK: 2 DOF BACK: 3 DOF SHOULDER: 3 DOF ELBOW: 1 DOF WRIST: 2 DOF HIP: 3 DOF KNEE: 1 DOF ANKLE: 1 DOF

• Hands attach through modular wrist
– Mechanical interface – Electrical & data interface

Actuator Design Targets Derived RoM in degrees Joint hip knee ankle mid foot back neck shoulder elbow wrist DoF 3 1 2 n/a 3 3 3 1 3 Adduction/Abduction (° rx) Flexion/Extension (° ry) Internal/Medial Rotation (° rz) min -30 max 30 range 60 min -100 0 -40 -35 -45 -90 -135 max 20 135 40 25 45 50 0 range 120 135 80 60 90 140 135 min -10 max 70 range 80 -40 0 -30 40 115 60 80 115 90 -45 -90 -40 -85 45 90 100 85 90 180 140 170 Joint hip knee ankle mid foot back neck shoulder elbow wrist DoF 3 1 2 0 3 3 3 1 3 Derived Strengths in Newton-Meters Adduction/Abduction (rx) Flexion/Extension (ry) Internal/Medial Rotation (rz) Strength Strength Strength 180 260 110 220 220 Passive Flexure 100 180 110 25 54 110 110 80 100 30 15 56 .

5 12.0 103 MASS [LBS] 67.Robot Weight Estimates • Weight estimate for current design: 178 lbs 3% 7% Pelvis & Leg Torso & Back Arm & Hand Head & Neck Hoses & Cables Skin Misc.8 10.6 4.5 22.1 5.6 178 48.5 227 13% 4% 2% 21% Fluid (Oil/Water) 38% 12% 57 .0 7.6 37.8 3.4 17.7 21.5 2. Hardware Fluid (Oil/Water) ROBOT TOTAL Power Plant TOTAL MASS [KG] 30.0 5.7 9.2 1.5 81 22. Hardware COMPONENT Pelvis & Leg Torso & Back Arm & Hand Head & Neck Hoses & Cables Skin Misc.

Power Tether • Tether – Electric power – Cooling water Power Pack Laboratory Electrical Power Cooling Water 58 .

LIDAR .Robot Computing Architecture GigE WIFI User Computer GigE Sensors CANbus CANbus Actuators (27) Joint Sensors Hands .Stereo Cameras Robot Computer .IMU .

Inc. . Nate Koenig Open Source Robotics Foundation.Mr.

and environments . actuators.Simulation for robots Focus on accurate physical simulation Easy transition to and from simulation Remove hardware issues and resource constraints Support common robot control software Custom client code ROS interface Player interface Support sharing of resources New sensors. models.

Additional Benefits No real-time constraints Simulate faster than real time Regression testing Use simulation for automated tests Universal test environment Create benchmarks Run a competition Flexibility Handles a wide range of environments and tasks Thin programmatic layer to Gazebo functionality .

.

.

.

.

.

Architecture Physics Visualization Interfaces Rigid Body Dynamics ODE Bullet OpenGL OGRE Plugins and IPC Google Protobuf Boost .

Robot Models Simple platforms Built-in shapes Mesh skinning Realistic physical properties Full sensor suite Meshes as collision objects Mass and inertia properties Surface friction 6 joint types Laser range finders Mono/Stereo cameras Kinect Contact Joint force/torques .

Environments Simple Focused scenario Manipulation Perception Indoor Path planning Mobile manipulation Clone real environment Aerial robots Outdoor mobile and legged robots Outdoor .

Show video with next slide Presenter will talk to it .

Gazebo Demo Part 1: Canyon fly-through Custom terrain generated from a greyscale image Animated quadrotor Thanks to Johannes Meyer and Stefan Kohlbrecher Part 2: Pioneer2dx and office environment Player interface used to drive the Pioneer2dx Laser range finder sensor visualization Part 3: PR2 and YouBot PR2 object manipulation using ROS Interactive markers Part 4: Character animation Experimental animation of characters using skeletons Thanks to Mihai Dohla .

Tools Command line tools System inspection Insert and remove models Graphical tools Model placement Joint and mass visualizations Sensor visualizations .

org .Resources Robot models Distributed in Gazebo Work in progress Online model database Graphical model builder Environments Distributed in Gazebo Google's 3D warehouse Google Sketchup or Blender Help http://gazebosim.

6 2.4 1. force-torque.Roadmap Bullet integration Multi-floor structures Sonar.0 Vehicles Tools Outdoor environments Cluster support Customize GUI API Large environments Vehicle suspension models . pressure sensors Friction and noise models Hardware in the loop Deformable objects 1.2 1.

org/projects/gazebo/ .org/wiki Kforge project https://kforge.Community Support and Contributing http://gazebosim.org/support.ros.html Wiki http://gazebosim.

Thank you Physics Lead John Hsu Core Contributor Mihai Dolha Contributors Christian Gagneraud Brian Gerkey Stefan Kohlbrecher Johannes Meyer Alexis Maldonado Jordi Polo Abbas Sadat Richard Vaughan Co-Founder: Retired Andrew Howard .

DARPA Robotics Challenge Proposers’ Day We are on a temporary break and will be back shortly 78 .

DARPA Robotics Challenge Proposers’ Day Q&A Response 79 .

DARPA Robotics Challenge Proposers’ Day Adjourn 80 .

Sign up to vote on this title
UsefulNot useful