Overview

 Introduction / Terminology
 Examples of Agencies
 SPOT & Fresh Kitty
 RoboCup
 Applications of AI and Robotics
 More Examples
 The Humanoid COG
 Film Clip

1
 INTRODUCTION

Robotics is an interdisciplinary integrative field, at the

confluence of several areas, ranging from mechanical and
electrical engineering to control theory and computer science,
with recent extensions toward material physics, bioengineering
or cognitive sciences. The AI–Robotics intersection is very rich.
It covers issues such as:
 • Deliberate action, planning, acting, monitoring and goal
reasoning,
 • Perceiving, modeling and understanding open
environments,
 • Interacting with human and other robots,
 • Learning models required by the above functions,
 • Integrating these functions in an adaptable and resilient
architecture.

2
 Robots
 Robota (Czech) = A worker of forced labor
From Czech playwright Karel Capek's 1921 play
“R.U.R” (“Rossum's Universal Robots”)
 Japanese Industrial Robot Association (JIRA) :
“A device with degrees of freedom that can be
controlled.”
 Class 1 : Manual handling device
 Class 2 : Fixed sequence robot
 Class 3 : Variable sequence robot
 Class 4 : Playback robot
 Class 5 : Numerical control robot
 Class 6 : Intelligent robot

3
 Terminology
 Artificial Intelligence – The collective attributes of a computer, robot, or
other device capable of performing functions such as learning,
decision making, or other intelligent human behaviors.
 Autonomous Agent – A hardware (or software) based system that has
the following properties:
autonomy - able to operate without the direct intervention of humans
or others
social ability - able to interact with other agents and possibly humans
reactivity - able to perceive their environment and respond to
changes that occur in it
 Agency – A particular system composed of intelligent agents, such as
computers or robots, that cooperate in order to solve a problem.
 Behavior Engineering – A methodology used to develop behavior- based
autonomous agents.

4
 A Brief History On Robotics
 Mechanical Automata
 Ancient Greece & Egypt
 Water powered for ceremonies
 14th – 19th century Europe
 Clockwork driven for entertainment
 Motor driven Robots
 1928: First motor driven automata
 1961: Unimate
(First industrial robot)
 1967: Shakey
Autonomous mobile research robot
 1969: Stanford Arm
Dextrous, electric motor driven robot arm

5
6
SPOT
 Autonomous mobile robot
 2 independent wheel design
 Max. speed of 1 foot/sec
 On-board microcontroller
supervises and supports the
exchange of information
 Turret that holds infrared
emitters that can be detected
at a distance of up to 20 feet
 Bumpers all around the robot
used to follow walls
 Radio modem to communicate
with remote agents

7
Fresh Kitty
 Modular, inexpensive,
autonomous mobile robot
 4 wheel toy car design
 Max. speed of 1 foot/sec
 On-board microcomputer
supervises and supports the
exchange of information
 Rotating turret holds 4 sonars
 Turret also holds an infrared
sensor to detect infrared rays
 32 light sensors detect objects in
front of the robot
 Bumpers all around the robot
used to follow walls
 Radio modem to communicate
with remote agents

8
How Do SPOT And Fresh Kitty Work
Together?

 SPOT also holds a small brush on its

back
 SPOT finds a wall and uses its bumper
system and sensors to follow edges
and collect dust with its brush
 Through radio frequency and infrared
communication SPOT can bring the
dust back to Fresh Kitty who has a
vacuum cleaner waiting to suck it up

9
10
 Robo Cup
Robo Cup is an international research effort to
promote autonomous robots.

 Robots must cooperate in…

 Strategy acquisition
 Real-time reasoning
 Multi-agent collaboration
 Competition against another
team of robots

11
Robo Cup

 Each robot has…

 Pentium 233MHz
 Linux OS
 Videocamera and
frame grabber
 Sensor System
 Kicker

12
How to the robots make decisions?
 Control is based on a set of behaviors
 Each behavior has a set of preconditions that
either…
 Must be satisfied
 Are desired

 A behavior is selected when all of the “musts”

become true
 A behavior is selected from several behaviors
based on how many desired conditions are true

13
 Behavior-Based
Robot Control Architectures
 Reactive, behavior-based control combines
relatively simple behaviors, each of which
achieves a particular subtask, to achieve the
overall task.
 Robot can react fast to changes
 System does not depend on complete knowledge of
the environment
 Emergent behavior (resulting from combining initial
behaviors) can make it difficult to predict exact
behavior
 Difficult to assure that the overall task is achieved
14
 Applications of AI and Robotics

 Industrial Automation
 Services for the Disabled
 Vision Systems
 Planetary Exploration
 Mine Site Clearing
 Law Enforcement
 And Many Others…

15
More Examples

16
17
The Humanoid COG

 MIT’s finest
 Broken down COG is just a
bunch of sensors and
actuators
 Except for legs and a flexible
spine, COG has all the major
degrees of freedom of the
human upper body
 Sight exists through video
cameras
 Hearing, touch, hand motion,
and speech are being added
soon

18
 Why build a human-like robot?

Brought to you by Rodney Brooks

 Our bodies are critical to the representations

that we use for internal thought and language
 If a robot is looks like a human then it will be
natural for humans to interact with it in a
human-like way
 To develop similar task constraints

19
 Hybrid Control Architectures
 Advantages
 Permits goal-based strategies
 Ensures fast reactions to unexpected changes
 Reduces complexity of planning

 Problems
 Choice of behaviors limits range of possible tasks
 Behavior interactions have to be well modeled to be
able to form plans

20
 "Social" Robot Interactions
 Advantages:
 Robots that look human and that show “emotions”
can make interactions more “natural”
 Humans tend to focus more attention on people than on
objects
 Humans tend to be more forgiving when a mistake is
made if it looks “human”
 Robots showing “emotions” can modify the way in
which humans interact with them
 Problems:
 How can robots determine the right emotion ?
 How can “emotions” be expressed by a robot ?

21
Requirements for Robots in Intelligent Environments

 Autonomy
 Robots have to be capable of achieving task objectives without
human input
 Robots have to be able to make and execute their own decisions
based on sensor information
 Intuitive Human-Robot Interfaces
 Use of robots in smart homes can not require extensive user
training
 Commands to robots should be natural for inhabitants
 Adaptation
 Robots have to be able to adjust to changes in the environment

22
Robots for Intelligent Environments

23
 Conclusions
 Robots are an important component in Intelligent
Environments
 Automate devices
 Provide physical services
 Robot Systems in these environments need particular
capabilities
 Autonomous control systems
 Simple and natural human-robot interface
 Adaptive and learning capabilities
 Robots have to maintain safety during operation
 While a number of techniques to address these
requirements exist, no functional, satisfactory solutions
have yet been developed
 Only very simple robots for single tasks in intelligent
environments exist

24