TECHNICAL SEMINAR
ON
Outline

 Definition of robots, robotics, behavior-based robotics
 Expression of behavior robots
 Behavior-based architectures
 History of robotics
 Applications
 Key issues
What is a Robot?

 Generally, it is a machine that
functions in place of a living agent
 "an automatic device that performs
functions normally ascribed to
humans or a machine in the form of
a human."
Robotics??
 Refers to study and use of robots.
 It’s a multi-disciplinary field.
 Best robotics researchers and
engineers will touch upon all disciplines:
 Mechanical engineering
 Electrical engineering
 Computer Science
 Computer science is concerned primarily with:
 Robot Programming
 Perception
 Intelligent behavior
Behavior-based Robotics??
 Behavior is what an external
observer sees a robot doing.
 Robots are programmed to
display desired behavior.
 Behavior is a result of a
sequence of robot actions.
 Observing behavior may not
tell us much about the
internal control of a robot.
 Control can be a black box.
Behavior-based Robotics??
(cont.)

 An intelligent robot is a machine able
to extract information from its
environment and use knowledge
about its world to move safely in a
meaningful and purposive manner.
Expressions of Behaviors
Stimulus

Behavior

 Stimulus-response (SR)
diagrams
 Functional notation
b(s) = r
 Finite state acceptor (FSA)
diagrams

Response
Types of State
 External state: state of the world
 Sensed using the robot’s sensors
 E.g.: night, day, at-home, sleeping, sunny

 Internal state: state of the robot
 Sensed using internal sensors
 Stored/remembered
 E.g.: velocity, mood

 The robot’s state is a combination of its
external and internal state.
State and Intelligence

 State space: all possible states the
system can be in
 A challenge: sensors do not provide
state!
 How intelligent a robot appears is
strongly dependent on how much it can
sense about its environment and about
itself.
Expressions of Behaviors
(cont)
 A Navigational Example
Consider a student going from one
classroom to another. The following
kinds of things are involved.
• Getting to the destination from
current location
• Not bumping into anything along the
way
• Skillfully negotiating the way around
other students
• Observing cultural customs
• Coping with change and doing
whatever else is necessary
Behavior-Based Architectures
 Definition
Robot architecture is the discipline devoted to the
design of highly specific and individual robots
from a collection of common software building
blocks.
Behavior-Based Architectures
(cont)
 Evaluation Criteria
• Supporting for parallelism
• Hardware targetability
• Support for modularity
• Robustness
• Timeliness in development
• Run time flexibility
• Performance effectiveness
Behavior-Based Architectures
(cont)
 A foraging example
The tasks consists of a robot’s moving away from a
home base area looking for attractor objects.
• Wander
• Acquire
• Retrieve
Behavior-Based Architectures
(cont)
 Subsumption architecture (Brooks)
•

AFSM model

•

It is a layered architecture that uses-



arbitration strategies and

 AFSM as its basis.
•

Coordination: Inhibition and suppression

•

Pros
 Hardware retarget ability
 Support for parallelism

•

Cons
 Run time flexibility
 Support for modularity
Behavior-Based Architectures
(cont)
 Motor schemas (Arkin)
• A schema is the basic unit
of behavior from which
complex actions can be
constructed; it consists of
the knowledge of how to act
or perceive as well as the
computational process by
which it is enacted.
• Motor schemas are a
software-oriented dynamic
reactive architecture that is
non-layered and
cooperative.
History of Robots
Classic
Purely mechanical machines. E.g. clock
tower, AL jazari’s musical robot etc.
Many machines that were capable of drawing, acting,
flying, playing music etc. E.g. eating duck.,
mechanical calculators.
Automation lead to programable machines. E.g.
Radio controlled boat.

Development of algorithms and
mathematical calculations; computer
science field arose.
G. Walter Grey's tortoise

These vehicles had
a light sensor,
touch sensor,
propulsion motor,
steering motor, and
a two vacuum tube
analog computer.
 Walter applied cybernetics principles to
robot design called “machine
speculatrix”, which became a robotic
tortoise.
 The simple principles involved are:
 Parsimony : simple is better.
 Exploration or speculation.
 Attraction.
 Aversion
 Discernment.
Middleware
HONDA developed its first
humanoid;

1981 to 1990
First industrial robot
was build by German
known as Famulus

1971 to 1980
Lunokhod 1, the
first moving remote
controlled robot
landed on moon
Bipolar transistor
discovered; first
comp game
beaten human in
chess; coined the
term ‘Artificial
Intelligence

1961 to 1970

1951 to 1960
Lunokhod 1
UNIMATE robot

First industrial
robot, that
Began to work at
general motor
KUKA- example of
industrial robot
They can load,
unload,
flame-machine,
laser, weld,
bond, assemble,
inspect, and
sort.
IBM 7535
 IBM 7535
Manufacturing
System
provided it
advanced
programming
functions,
including data
communication
s,
programmable
speed.
Cog – MIT AI Lab
Cog is a humanoid
robot. It has a torso,
arms and a head but
no legs. Cog's torso
does not have a spine
but it can bend at the
waist from side-toside and from frontto-back and can twist
its torso the same way
a person can. Cog's
arms also move in a
natural way.
Snake-like robot

 

                                                

                                          

A. Hirose (Tokyo IT)
Snake (MIT) and Swimming (Eel)
Robot (UHK)
LEGO Mindstorms
Present Era
2010 to Present
2001 to 2010
1991 to 2000
Honda revealed the
most advanced
humanoid robot
ASIMO i.e. capable of
running, walking,
communication with
humans, facial and
environment
recognition, voice and
posture recognition
and interact with
environment.

This era experienced
highly advance
robotics like iRobot
humanoid which had
more enhanced
feature than ASIMO,
Unmanned Aerial
Vehicle Global Hawk,
etc.

Robonaut 2, the latest
generation robot
called “The space
walker”.
Google’s robotic
vehicles “The self
driving car” is the
latest development in
History of Robotics.
Asimo

Honda announced the
development of new
technologies for the
next-generation
ASIMO humanoid
robot, targeting a
new level of mobility.


Unmanned Vehicles
Robonaut 2
oUses space
tools.
oWorks in similar
environments
suited to
astronauts.
o Very sensible.
oEssential to
NASA’s future.
Wheelesley: Development of a
Robotic Wheelchair System
 Wheelesley, consists of
an electric wheelchair
outfitted with a
 computer and sensors
and a Macintosh
Powerbook that is used
 for the user interface
The Robot Dog Aibo
Artificial Intelligence roBOt
intelligent life form.
Good Boy! Aibo
"Good Boy!" Sony’s AIBO could learn
whatever name you give your AIBO.
With built-in voice recognition, AIBO
could learn up to fifty words (later Aibo
models could do one thousand words)
and talk back to you in a special AIBO
tonal language. You command your
pet to follow orders including "take a
picture." AIBO has a built in camera.
That is something your real life pet
cannot do.
Suvelliance Humanoid Robot
NUVO
 Equipped with
survelliance
camera at head
and owner could
monitor the
footage through
mobile phone
Anthropomorphic Robots
Applications

Entertainment
Explorations
Humanoids
Assistants,
In Medical
Educational

Transport
Key Issues
 Grounding in reality: not just
planning in an abstract world
 Situatedness (ecological
dynamics): tight connection with
the environment
 Embodiment: having a body
 Emergent behavior: interaction
with the environment
 Scalability: increasing task and
environment complexity
Questions??

Behavior-based robotics

  • 1.
  • 2.
    Outline  Definition ofrobots, robotics, behavior-based robotics  Expression of behavior robots  Behavior-based architectures  History of robotics  Applications  Key issues
  • 3.
    What is aRobot?  Generally, it is a machine that functions in place of a living agent  "an automatic device that performs functions normally ascribed to humans or a machine in the form of a human."
  • 4.
    Robotics??  Refers tostudy and use of robots.  It’s a multi-disciplinary field.  Best robotics researchers and engineers will touch upon all disciplines:  Mechanical engineering  Electrical engineering  Computer Science  Computer science is concerned primarily with:  Robot Programming  Perception  Intelligent behavior
  • 5.
    Behavior-based Robotics??  Behavioris what an external observer sees a robot doing.  Robots are programmed to display desired behavior.  Behavior is a result of a sequence of robot actions.  Observing behavior may not tell us much about the internal control of a robot.  Control can be a black box.
  • 6.
    Behavior-based Robotics?? (cont.)  Anintelligent robot is a machine able to extract information from its environment and use knowledge about its world to move safely in a meaningful and purposive manner.
  • 7.
    Expressions of Behaviors Stimulus Behavior Stimulus-response (SR) diagrams  Functional notation b(s) = r  Finite state acceptor (FSA) diagrams Response
  • 8.
    Types of State External state: state of the world  Sensed using the robot’s sensors  E.g.: night, day, at-home, sleeping, sunny  Internal state: state of the robot  Sensed using internal sensors  Stored/remembered  E.g.: velocity, mood  The robot’s state is a combination of its external and internal state.
  • 9.
    State and Intelligence State space: all possible states the system can be in  A challenge: sensors do not provide state!  How intelligent a robot appears is strongly dependent on how much it can sense about its environment and about itself.
  • 10.
    Expressions of Behaviors (cont) A Navigational Example Consider a student going from one classroom to another. The following kinds of things are involved. • Getting to the destination from current location • Not bumping into anything along the way • Skillfully negotiating the way around other students • Observing cultural customs • Coping with change and doing whatever else is necessary
  • 11.
    Behavior-Based Architectures  Definition Robotarchitecture is the discipline devoted to the design of highly specific and individual robots from a collection of common software building blocks.
  • 12.
    Behavior-Based Architectures (cont)  EvaluationCriteria • Supporting for parallelism • Hardware targetability • Support for modularity • Robustness • Timeliness in development • Run time flexibility • Performance effectiveness
  • 13.
    Behavior-Based Architectures (cont)  Aforaging example The tasks consists of a robot’s moving away from a home base area looking for attractor objects. • Wander • Acquire • Retrieve
  • 14.
    Behavior-Based Architectures (cont)  Subsumptionarchitecture (Brooks) • AFSM model • It is a layered architecture that uses-  arbitration strategies and  AFSM as its basis. • Coordination: Inhibition and suppression • Pros  Hardware retarget ability  Support for parallelism • Cons  Run time flexibility  Support for modularity
  • 15.
    Behavior-Based Architectures (cont)  Motorschemas (Arkin) • A schema is the basic unit of behavior from which complex actions can be constructed; it consists of the knowledge of how to act or perceive as well as the computational process by which it is enacted. • Motor schemas are a software-oriented dynamic reactive architecture that is non-layered and cooperative.
  • 16.
  • 17.
    Classic Purely mechanical machines.E.g. clock tower, AL jazari’s musical robot etc. Many machines that were capable of drawing, acting, flying, playing music etc. E.g. eating duck., mechanical calculators. Automation lead to programable machines. E.g. Radio controlled boat. Development of algorithms and mathematical calculations; computer science field arose.
  • 18.
    G. Walter Grey'stortoise These vehicles had a light sensor, touch sensor, propulsion motor, steering motor, and a two vacuum tube analog computer.
  • 19.
     Walter appliedcybernetics principles to robot design called “machine speculatrix”, which became a robotic tortoise.  The simple principles involved are:  Parsimony : simple is better.  Exploration or speculation.  Attraction.  Aversion  Discernment.
  • 20.
    Middleware HONDA developed itsfirst humanoid; 1981 to 1990 First industrial robot was build by German known as Famulus 1971 to 1980 Lunokhod 1, the first moving remote controlled robot landed on moon Bipolar transistor discovered; first comp game beaten human in chess; coined the term ‘Artificial Intelligence 1961 to 1970 1951 to 1960
  • 22.
  • 23.
    UNIMATE robot First industrial robot,that Began to work at general motor
  • 24.
    KUKA- example of industrialrobot They can load, unload, flame-machine, laser, weld, bond, assemble, inspect, and sort.
  • 25.
    IBM 7535  IBM7535 Manufacturing System provided it advanced programming functions, including data communication s, programmable speed.
  • 26.
    Cog – MITAI Lab Cog is a humanoid robot. It has a torso, arms and a head but no legs. Cog's torso does not have a spine but it can bend at the waist from side-toside and from frontto-back and can twist its torso the same way a person can. Cog's arms also move in a natural way.
  • 27.
  • 28.
    Snake (MIT) andSwimming (Eel) Robot (UHK)
  • 29.
  • 30.
    Present Era 2010 toPresent 2001 to 2010 1991 to 2000 Honda revealed the most advanced humanoid robot ASIMO i.e. capable of running, walking, communication with humans, facial and environment recognition, voice and posture recognition and interact with environment. This era experienced highly advance robotics like iRobot humanoid which had more enhanced feature than ASIMO, Unmanned Aerial Vehicle Global Hawk, etc. Robonaut 2, the latest generation robot called “The space walker”. Google’s robotic vehicles “The self driving car” is the latest development in History of Robotics.
  • 31.
    Asimo Honda announced the developmentof new technologies for the next-generation ASIMO humanoid robot, targeting a new level of mobility. 
  • 32.
  • 33.
    Robonaut 2 oUses space tools. oWorksin similar environments suited to astronauts. o Very sensible. oEssential to NASA’s future.
  • 34.
    Wheelesley: Development ofa Robotic Wheelchair System  Wheelesley, consists of an electric wheelchair outfitted with a  computer and sensors and a Macintosh Powerbook that is used  for the user interface
  • 35.
    The Robot DogAibo Artificial Intelligence roBOt intelligent life form. Good Boy! Aibo "Good Boy!" Sony’s AIBO could learn whatever name you give your AIBO. With built-in voice recognition, AIBO could learn up to fifty words (later Aibo models could do one thousand words) and talk back to you in a special AIBO tonal language. You command your pet to follow orders including "take a picture." AIBO has a built in camera. That is something your real life pet cannot do.
  • 36.
    Suvelliance Humanoid Robot NUVO Equipped with survelliance camera at head and owner could monitor the footage through mobile phone
  • 37.
  • 38.
  • 39.
    Key Issues  Groundingin reality: not just planning in an abstract world  Situatedness (ecological dynamics): tight connection with the environment  Embodiment: having a body  Emergent behavior: interaction with the environment  Scalability: increasing task and environment complexity
  • 41.