ROBOTICS

1
ROBOTICS

• From the book
• Robin R. Murphy, Introduction to AI Robotics,
  The MIT Press

2
What Are Robots?

• The word robot
• Rossums Universal Robots
• January 25, 1921
• First performance of Karel Capeks play
• Derived from the Czech word robota which means
  menial laborer
• An Intelligent Robot
• A mechanical creature which can function
  autonomously

3
Robotic Paradigms

• Hierarchical
• Reactive
• Hybrid deliberative/reactive

4
What are Robotic Paradigms?

• Paradigm
• A philosophy or set of assumptions and/or
  techniques which characterize an approach to a
  class of problems
• Applying the right paradigm makes problem solving
  easier
• Three paradigms for organizing intelligence in
  robots
• Hierarchical paradigm
• Reactive paradigm
• Hybrid deliberative/reactive paradigm

5
Robotic Paradigms

• The paradigms can be described in two ways
• By the relationship between the three commonly
  accepted primitives
• By the way sensory data is processed and
  distributed through the system.

ROBOT PRIMITIVES INPUT OUTPUT
SENSE Sensor data Sensed information
PLAN Information (sensed and/or cognitive) Directives
ACT Sensed information or directives Actuator commands
6
Hierarchical Paradigm

• The oldest paradigm (1967-1990)
• Top-down fashioned operation
• Heavy on planning
• Control people hated because it isnt close the
  loop
• AI people hated because monolithic
• Users hated because very slow

7
Reactive Paradigm
SENSE-ACT couplings are behaviors
Behaviors are independent, run in parallel

• Heavily used in 1988-1992
• Users loved it because it worked
• AI people loved it, but wanted to put PLAN back
  in
• Control people hated it because couldnt
  rigorously prove it worked

8
Hybrid deliberative/reactive paradigm

• Control people hated it because AI, but are
  getting over it
• AI people loved it
• Users loved it

9
How AI related to a robot system?

• Deliberative
• Upper level is mission generation monitoring
• But World Modeling Monitoring is hard
• Lower level is selection of behaviors to
  accomplish task (implementation) local
  monitoring

• Reactive (fly by wire, inner loop control)
• Many concurrent stimulus-response behaviors,
  strung together with simple scripting
• Action is generated by sensed or internal
  stimulus
• No awareness, no monitoring
• Models are of the vehicle, not the larger world

10
How AI related to a robot system?
PLAN
SENSE
ACT

• Converting sensor data into information
• Promising results ATR, single failure health
  monitoring
• Open issues creation of world models
  situation awareness, monitoring detection of
  new threats, exceptions, opportunities

• Reasoning over information about goals
• Promising results Navigation, payload planning,
  contingency replanning
• Open issues Multi-agent replanning, fault
  recovery reconfiguration, reasoning over
  multiple failures

Skills and responses
11
New trends on the horizon

• Shape-Shifting
• Legged Platform
• Humanoids

12
Shape Shifting

• Snake-like robots
• Rescue site
• Narrow passage
• Tracked vehicles
• Rough terrain
• Robust to turnover
• Robot bugs
• Ecological approach
• High mobility

13
Legged Locomotion

• Advantages
• Moving through rugged terrain
• Low power consumption
• Examples
• Hexapod
• One-, two-, four-legged
• Major issues
• Maintaining balance
• Getting up / sitting down
• Dynamically adapting the gaits to terrain

14
Close proximity with human

• Aibo
• The best known robot pet
• Non-verbal communication with human
• Kismet
• Facial robot
• Physically expressive interfaces
• Minerva
• Tour guide robot
• Expressive face

15
Humanoids

• Famous humanoids
• ASIMO, HONDA
• AMI, KAIST
• HUBO, KAIST
• ROBONAUT, NASA
• COG, MIT