david vernon short intro to robotics and ai

8/6/2019 David Vernon Short Intro to Robotics and AI

1/79


2/79

Copyright 2007 David Vernon (www.vernon.eu)

A Short Introduction to

Robotics and AI


3/79


Learning Objectives

Nature of robotics

Robotic applications

Principal engineering issues

Principal AI issues The future of robotics


4/79


The Word Robot

Robot is derived from a Czech word meaningforced labor

First appeared in a 1920 play R.U.R.(Rossums Universal Robots)

by Czech playwright Karel Capek.


5/79


Definitions

"A reprogrammable, multifunctional manipulator designedto move material, parts, tools, or specialized devicesthrough various programmed motions for theperformance of a variety of tasks

Robot Institute of America


6/79


Types of Robot

Manipulators


7/79


Unimate Puma Robot


8/79


Adept's SCARA robots,images courtesy ofAdept Technology


9/79


Stubli's RX130manipulators, images

courtesy of Stubli


10/79


CRS' F3 robot testing amobile phone, image

courtesy of CRS

Robotics


11/79


BH8-260 Hand from Barrett Technology,

image courtesy of Barrett


12/79


The Space Station Remote Manipulator System (SSRMS)

Canadarm - Robot arm on every Space Shuttle, image courtesy of

the Canadian Space Agency


13/79



14/79


Types of Robot

Manipulators

Mobile robots


15/79


Urban Robot Platform - image courtesy of

NASA JPL

Urban Robot Platform - image courtesy of NASA JPL


16/79


iRobot-LE - imagecourtesy of iRobot


17/79


Oberon - underwater robot developed by the

Australian Centre for Field Robotics


18/79


Dante II robot, imagecourtesy of NASA


19/79


Mars Sojourner, image courtesy of NASA



20/79


Mars Sojourner, image courtesy of NASA



21/79


Honda's P1 HumanoidRobot

(controlled via tether)


22/79


Honda's P3 Robot


23/79


Honda's ASIMO Robot


24/79


Honda's ASIMO Robot


25/79


Types of Robot

Manipulators

Mobile robots

Entertainment


26/79


Sony's 1st Generation

Aibo Robot Dog


27/79


28/79


29/79


30/79


31/79


32/79


33/79


MIT AI Lab COG

(with Rodney Brooks)


34/79


35/79


iCub

(www.iCub.org)


36/79


37/79


Robotic Applications Parts handling

Assembly Painting

Surveillance

Security (bomb disposal really telechericsrather than robotics)

Home help (grass cutting, nursing)


38/79


39/79


40/79


CMU Nursebot project

FLO


41/79


42/79


43/79


Exploration


44/79


45/79


Mechanical Construction

ControllerArm

Drive

End Effectors

SensorPlease click over the picture


46/79


47/79


48/79


49/79


Trajectory Generation

Cartesian space vs. Joint Space

Manipulator kinematics (given joint angles, find positionand orientation of end effector)

Inverse kinematics (given position and orientation ofend effector, find joint angles)

Dynamics


50/79


51/79


Trajectory Generation

Problems with Cartesian space interpolation

Unreachable configurations

Multiple solutions

Task Specification & World


52/79


as Spec cat o & o d

Modelling

Specification of orientation:

Use transformation matrices and Eulerangles or Roll-Pitch-Yaw convention

+

+

=

=

ccscs

sccssccssscs

sscsccsssccc

cs

sc

cs

sc

cs

sc

RXYZ

A

B

0

0

001

0

010

0

100

0

0

),,(


53/79


54/79


AI & Robotics

Interaction with the environment


55/79


The Real World

Uncertain, Incomplete, Time-varying

From Introduction to AI Robotics, Robin Murphy


56/79


AI &Robotics

Agent based examples taken from:Q. Tipu, University of Southern California


57/79


AI & Robotics How to represent knowledge about the world?

How to react to new perceived events? How to integrate new percepts to past experience?

How to understand the user?

How to optimize balance between user goals & environment constraints? How to use reasoning to decide on the best course of action?

How to communicate back with the user?

How to plan ahead? How to learn from experience?


58/79


59/79


60/79


61/79


62/79


Agent Types

We can split agent research into two main strands:

Distributed Artificial Intelligence (DAI) Multi-Agent Systems (MAS) (1980 1990)

Much broader notion of "agent"(1990s present) interface, reactive, mobile, information


63/79


Towards Autonomous Vehicles

http://iLab.usc.edu

http://beobots.org


64/79


Interacting Agents

Lane Keeping Agent (LKA) Goals: Stay in current lane

Percepts: Lane center, lane boundaries

Sensors: Vision Effectors: Steering Wheel, Accelerator, Brakes

Actions: Steer, speed up, brake

Environment: Freeway


65/79


Interacting Agents

Collision Avoidance Agent (CAA) Goals: Avoid running into obstacles

Percepts: Obstacle distance, velocity, trajectory

Sensors: Vision, proximity sensing

Effectors: Steering Wheel, Accelerator, Brakes, Horn, Headlights

Actions: Steer, speed up, brake, blow horn, signal (headlights)

Environment: Freeway


66/79

The Right Thing =


67/79


The Rational Action Rational Action: The action that maximizes the

expected value of the performance measure given

the percept sequence to date

Rational = Best ?

Rational = Optimal ? Rational = Omniscience ?

Rational = Clairvoyant ?

Rational = Successful ?


68/79


69/79


Behavior and performance of IAs

Perception (sequence) to Action Mapping: f: P* A

Ideal mapping: specifies which actions an agent ought to take at anypoint in time

Description: Look-Up-Table vs. Closed Form

Performance measure: a subjectivemeasure to characterize how

successful an agent is (e.g., speed, power usage, accuracy, money,etc.)

(degree of) Autonomy: to what extent is the agent able to make

decisions and actions on its own?

How is an Agent different from other


70/79


software?

Agents are autonomous, that is they act on behalf of the user Agents contain some level of intelligence, from fixed rules to learning

engines that allow them to adapt to changes in the environment

Agents don't only act reactively, but sometimes also proactively

Agents have social ability, that is they communicate with the user, thesystem, and other agents as required

Agents may also cooperate with other agents to carry out more complextasks than they themselves can handle

Agents may migrate from one system to another to access remote

resources or even to meet other agents


71/79


Agent types Reflex agents

Reflex agents with internal states Goal-based agents

Utility-based agents


72/79


Reflex agents


73/79


74/79


Reflex agents w/ state


75/79


Goal-based agents


76/79


Utility-based agents


77/79


Anticipate

AssimilateAdapt

Action Perception

Cognition


78/79

simulated sensory signals

Perturbation


79/79


Phylogenetic self-organizingperceptuo-motor skills

Modulation circuit:homeostatic action selection

by disinhibition of perceptuo-motor skills

Motivation(Amygdala)

Auto-associativeMemory

(Hippocampus)

ActionSelection

(Basal Ganglia)

Motor/SensoryAuto-associative

Memory

Sensory/MotorAuto-associative

Memory

simulated motor signals

Prospection by

action simulation

Perturbation

david vernon short intro to robotics and ai

Documents