Intelligent Machines & Systems

Perspectives for the course

(Introductory Session 2021)

Dr. C.S.Kumar
Robotics and Intelligent Systems Lab
CAD-CAM &Direct Digital Manufacturing Lab
IIT Kharagpur
 Different scenarios
• Manufacturing (in Industry) for Engineers
– Why is “Intelligent Systems” relevant here?
• Robotics
• Autonomous Systems
• Other Applications
• Types of Intelligent Systems applications
• Current Trends
 Developments in Manufacturing
Automation
STAGE FEATURE AUTOMATION DESIGN MANUFACTURE

1 Labour Intensive None Individual Manual

2 Equipment-intensive Instruments Group NC,CNC

3 Information-Intensive Information CAD FMS

4 Knowledge-Intensive Decision ICAD CIMS

 Generations of Industries

Trending Today – Industry 4.0 / Manufacturing 4.0

Source: Wikipedia
 Academic-Research Perspective

Integrated and Intelligent Manufacturing: Perspectives and Enablers

Yubao Chen
Department of Industrial and Manufacturing Systems Engineering, University of Michigan
In Special Issue on Engineering (Elsevier)
Pages 588-595
• “The future will be characterized by smart
devices delivering increasingly insightful
digital services everywhere,” said David
Cearley, Gartner Distinguished Vice
President Analyst, at Gartner 2018
Symposium/ITxpo in Orlando, Florida. “We
call this the intelligent digital mesh.”
• Intelligent: How AI is in virtually every
existing technology, and creating entirely
new categories.
• Digital: Blending the digital and physical
worlds to create an immersive world.
• Mesh: Exploiting connections between
expanding sets of people, businesses,
devices, content and services.
• “Trends under each of these three themes
are a key ingredient in driving a
continuous innovation process as part of
the continuous next strategy,” Cearley
said.
Fig. 2 presents a framework of the
Industry 4.0 IMS, in which research
topics are categorized into smart design,
smart machines, smart monitoring, smart
control, and smart scheduling.
•
Various platforms for ML workflow

PTC
GE

Microsoft
Framework of the Industry 4.0 IMS
• Smart design. With the rapid development of new technologies such as VR and augmented reality (AR),
traditional design will be upgraded and will enter into a “smart era.” Design software such as computer-aided
design(CAD) and computer-aided manufacturing (CAM) is able to interact with physical smart prototype systems
in real time, enabled by three-dimensional (3D) printing integrated with CPSs and AR.

• Smart machines. In Industry 4.0, smart machines can be achieved with the help of smart robots and various
other types of smart objects that are capable of real-time sensing and of interacting with each other. For
example, CPS-enabled smart machine tools are able to capture real-time data and send them to a cloud-based
central system so that machine tools and their twinned services can be synchronized to provide smart
manufacturing solutions.

• Smart monitoring. Monitoring is an important aspect for the operations, maintenance, and optimal scheduling
of Industry 4.0 manufacturing systems. The widespread deployment of various types of sensors makes it
possible to achieve smart monitoring. For example, data and information on various manufacturing factors such
as temperature, electricity consumption, and vibrations and speed can be obtained in real time.

• Smart control. In Industry 4.0, high-resolution, adaptive production control (i.e., smart control) can be
achieved by developing cyber-physical production-control systems. Smart control is mainly executed in order to
physically manage various smart machines or tools through a cloud-enabled platform. End-users are able to
switch off a machine or robot via their smart phones.

• Smart scheduling. The smart scheduling layer mainly includes advanced models and algorithms to draw on
the data captured by sensors. Data-driven techniques and advanced decision architecture can be used for smart
scheduling. For example, in order to achieve real-time, reliable scheduling and execution, distributed smart
models using a hierarchical interactive architecture can be used.
Intelligent Manufacturing in the Context of Industry 4.0: A Review
Ray Y.Zhong, XunXu, EberhardKlotz, Stephen T.Newman
Elsevier Engineering 2017 (http://dx.doi.org/10.1016/J.ENG.2017.04.009)
 Internet of Things in Manufacturing
GLOBAL
MANUFACTURING GLOBAL FACILITY CUSTOMER SITE OPERATIONS
PLANT INSIGHT I can see my
Transmits operational production
Monitor Remotely Manage line status
information to the
production Equipment partner (e.g. OEM) and and
Manage recommend
flow in near- to field service rs adjustments
engineers
real time to better
manage
Ioperational
gain
cost.
insight into
usage
patterns
R&D from
multiple
customers
and track
Identify and Provide cross-channel equipment
visibility into deterioratio
correct I know
inventories. n.
quality when to
deploy the
Condition-based issues. Plant right
Inventory Floor resources
maintenance.
Management for
Predictive predictive
maintenance maintenanc
THIRD-PARTY LOGISTICS e.
Intelligent Digital
Mesh
• Connected
Devices
• Real time digital
Data uptake
• Analytics
• Responsive
feedback
• Customer
Experience ?
 Problems in Industry
• Too much information needs manipulation
• Highly computerized human-machine system needs a
good quality interaction between operator and the
system.
• Involvement of different sections-- conflicts /conflict
resolution and reasoning strategies
• Large amount of data: How to process? How to
export effectively knowledge?
Types of Intelligent Manufacturing
Systems
TYPE FEATURES
TYPE I Symbolic Reasoning System
TYPE II Compiling IS that links numerical computation
programs with symbolic reasoning system
TYPE III ANN that model the human brain and deal with
empirical data
TYPE IV Integrated distributed IS involving expert systems,
numerical programs, neural nets and computer
graphics packages
 Hierarchical levels in Manufacturing
There are 3 basic levels of control
• Organization level
• Co-ordination level
• Execution level
 Organization level
1. Product design
2. Process planning
3. Master production scheduling
4. Forecasting
5. Strategic business planning
 Coordination Level
• Making short -term decisions based on inputs
provided by organization level
• Detailed scheduling
• Assembly operations
• Work and purchase order generations form.
 Execution Level
1. Appropriate control functions and detail feed back
from actual operations of manufacturing units
2. Provides supply of info to the coordination level for
possible revisions of short-term decisions and also
satisfactory
3. Database for knowledge and long term strategies
process monitoring and control
4. Adaptive control
5. Manufacturing system diagnostic
 ABSTRACT MODELS ALGORITHMS &
EXTENSIVE SEARCH
INFORMATION AND KNOWLEDGE FEEDBACK INFORAMTION
THROUGH ELECTRONIC MEDIA KNOWLEDGE ELECTRONIC
WITHIN LARGE TIME INTERVAL MEDIA IN MODERATE
TIME INTERVAL
LOCALIZED MODELS
MODERATE SEARCH
ATTRIBUTE MEASUREMENT
DATA INTEGARTION

DATA AND INFORMATION FEED BACK INFO THROUGH

THROUGH ELECTRONIC MEDIA ELECTRONIC MEDIA WITHIN
WITH IN MODERATE TIME SMALL TIME INTERVAL
INTERVAL

SENSORY DATA & FEEDBACK

NO SEARCH

INTELLIGENT FEEDBACK
CONTROL

SENSORS AND ACTUATORS

 Summary of requirements
EXTENSIVE SEARCH
ORGANISATION LEVEL ABSTRACT MODEL
LOW PRECISION
ALGORITHM

MODERATE SEARCH LOCALIZED MODELS

COORDINATION LEVEL ATTRIBUTE

MODERATE
PRECISION MEASUREMENT

DATA INTEGRATION
NO SEARCH SENSORY DATA
EXECUTION LEVEL FEEDBACK
HIGH PRECISION
SMALL TIME IMCREMENTS
Relevance in Industry Today

Integrated and Intelligent

Manufacturing: Perspectives
and Enablers

Yubao Chen
Department of Industrial and Manufacturing
Systems Engineering, University of Michigan

In Special Issue on Engineering (Elsevier)

Pages 588-595
 What is Intelligence?
“The ability of the system to act appropriately in an
uncertain environment, where appropriate action is
that which increases the probability of success, and
success is the achievement of behaviors sub-goals that
support the systems ultimate goal"
Criteria of success and ultimate goal defined external
to the I.S.

J. Albus, “Outline for a Theory of Intelligence,” IEEE

Transactions on Systems, Man, and Cybernetics, Vol.
21, No. 3, May/June, 1991, pp. 473-509
 3 Degrees of Intelligence

• COMPUTATION POWER

• COMPLEXITY OF THE ALGORITHMS USED BY THE SYSTEM

PROCESSING INPUT AND SOPHISTICATION OF SYSTEM
ELEMENTS

• THE INFORMATION AND VALUES STORED INSYSTEM

MEMORY
 4 Elements of Intelligent Systems
• SENSORY PROCESSING
• WORK MODEL
• VALUE JUDGEMENT
• BEHAVIOUR GENERATION
 Case: IOT and Wearable Technologies

Business Models for Internet of Things and Wearables; Joseph Wei, Lab 360, Chair IEEE
Santa Clara
Wearable Tech design strategies
 Case: Disney Magic Band

SCAN Code tags quite effective in TTD Temples

Why not have RFID and Wearable IoT device for
IR passengers?
New value
capture

New value
creation
 Case: Smart Home

Enhanced
response and
experience with
Alexa (voice
controlled
interaction)

Personalised
 Customer in the Loop

CuteLoop project (Customer in the Loop: Using

Networked Devices Enabled Intelligence for Proactive
Customers Integration as Drivers of Integrated
Enterprise – http://www.cuteloop.eu)
Direct Human Interaction
Bionics
Bionic Controls
 Generations of Intelligent Systems
• AI based systems
• Connectionist and Machine Learning
• Agent Based Systems
• Evolutionary Systems
• Cognitive Systems, Cybernetic and Cyber
Physical Systems
 AI and ML Time Lines

• Type 1
https://en.wikipedia.org/wiki/Symbolic_artificial_int
elligence
• AI History / Timelines
• https://en.wikipedia.org/wiki/History_of_artifici
al_intelligence

• https://en.wikipedia.org/wiki/Timeline_of_mach
ine_learning
• https://en.wikipedia.org/wiki/Artificial_general_i
ntelligence
• https://en.wikipedia.org/wiki/Deep_learning
• https://en.wikipedia.org/wiki/Big_data
 AI based Systems
• Expert Systems
• Rule based
• Knowledge expert
• Very rigid formulations
• Fragile to unknown situations
Connectionist & Machine Learning
• Neural Network based
– Biological neurons analogy
– Different learning theories
• Fuzzy Logic based
– Distributed memory based
– Rule based
• Redundancy and Robustness
 Agent based Systems
• Distributed intelligence
• Specialist knowledge
• Interaction between subsystems
• Complex Behaviors
• Subsumption architecture
• Intelligent Robotics
 Evolutionary Intelligent Systems
• Genetic Algorithms
• Based on natural evolution theories
• Adaptability
• Evolution and optimization
• Complex learning behaviors
• Emergent behaviours
Neural network based intelligence

• Connectionist Approach
• Machine Learning
• Cognitive Sciences
• Cognitive Architectures
• (Bio)Neuro-Cybernetics

• Cognitive Computing
• Computational Models for
Cognition
 Intelligent Robotics
• Platform for developing and evolving
Intelligent systems
• Lab and large scale versions available
• Ease of deployment as test beds
• Competition versions popular in students
 Different Directions of IS in Robotics
• Service and Assistive Robotics
• Autonomous Robots
• Rehabilitation
• Cognitive Robotics
• Swarm Robotics
 Components
• Interdisciplinary programs – ME, EE, CSE (AI),
Bio-medical
• New innovations and IP in sensors, algorithms
• New definitions of safety, programmability
• Adaptable intelligent behaviour
 Exploratory Robotics
• Remotely operated vehicles
• Autonomous vehicles
• Ground vehicles – wheeled, legged, hybrid
• Ariel Vehicles – UAVs,
• Underwater – ROVs, AUVs, UUVs
• Space Robotics
• Inter planetary rovers
 Autonomous Systems
• Systems which can work on their own without
external guiding inputs
• Sense and react with environment
• Decide on control actions on their own
• Intelligent systems
• Autonomous Robots
• Autonomous Vehicles
 Typical Areas Covered
• Sensors and Control in Mechatronics and Robotics
• Electronics for Mechanical Engineers
• Mechanical Engineering for Electronics Engineers
• Robotic Control and Networking
• Example cases of IIT Kharagpur
– Underwater Robotics
– Multi fingered hand
– Humanoid Robots
 Desire to build Intelligent Systems
• Robot Child Cat “Robokoneko” at ATR Labs
– CAMBrain Project
• Honda ASIMO
– Humanoid mobility
• SONY Aibo
– Intelligent Dog
• Fujitsu HOAP; Aldebran Nao
• ….
Robokoneko (robot kitten)
Mechanical design
 Activities it can do
Walk Steer
Jump

Programmed using Cellular Neural Networks

Unsupervised learning from simulated models

Controller developed on a chip called “CAMBrain”

 Honda Humanoid Robot Asimo

http://en.wikipedia.org/wiki/ASIMO

http://asimo.honda.com
 Humanoid Robot Nao

Aldebran Robotics
Kuka You Bot
 Autonomous Robots
• Respond to inputs on their own (no human
intervention)
• Recovery from failures
• Embodied intelligence
• Swam robots – cooperative situations
 Robotics
• Home: iRobot : vacuum and
cleaning robot (Roomba)
• Sophia (Hanson Robotics)
• Teslabot
• Industry:
• Collaborative Robots : Cobots
• Surgical Robots :
 Cars
• Autonomous Vehicles or Self
Driving Cars
• Advanced Driver Assistance
System (ADAS)
DDPAI Z40 Dashcam
• Automation versus Autonomy Tata Nexon EV https://en.ddpai.com/news
MIC /214.html

https://m.futurecar.com/4296/Teslas-Autopilot-is-Rated-as-the-Best-Advanced-
Driver-Assistance-System-in-China
 Regular Articles

• https://www.brookings.edu/resear
ch/how-artificial-intelligence-is-
transforming-the-world/
• https://www.mcca.com/wp-
content/uploads/2018/04/Autono
mous-Vehicles.pdf
• https://hbr.org/2018/07/collaborati
ve-intelligence-humans-and-ai-are-
joining-forces
• https://www.nature.com/natmachi
ntell/volumes/3
 Other emergent examples

• https://builtin.com/artificial-intelligence/examples-ai-in-industry
• https://www.analyticsinsight.net/top-10-artificial-intelligence-technologies-
making-a-breakthrough-in-2021/

• Robotic Process Automation (RPA) :

– UIPath (https://www.uipath.com)
– Automation Anywhere (https://www.automationanywhere.com)
– Blue Prism (https://www.blueprism.com)
– Pegasystems (https://www.pega.com)
 Some perspectives of others
• The future of the internet is intelligent
machines by Jeff Immelt, Chairman and CEO
of GE (on 28th Nov 2012)
• Internet of Things
• Socially Intelligent Machines Lab (Georgia
Tech)
• Super Intelligent Machines (Live Science
 Summary
• Intelligent Systems: Basic needs highlighted
• Precision verses adaptability discussed
• Types of implementations highlighted
• Focus on Connectionistic learning, Knowledge
based sytems etc
• Case for Robotics
• Examples in Robotics