CS 8520: Artificial Intelligence

bouncerarcheryΤεχνίτη Νοημοσύνη και Ρομποτική

14 Νοε 2013 (πριν από 3 χρόνια και 10 μήνες)

100 εμφανίσεις

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

CS 8520: Artificial Intelligence

Robotics


Paula Matuszek

Spring, 2010

2

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

2

What is your favorite robot?

HAL 9000. 2001, A
Space Odyssey: 1968

Wall
-
e: 2008

Data. Star Trek: TNG: 1987

Robby. Forbidden
Planet: 1956

Cylons and

Centurion. BSG:

2009.

3

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Some 21st century robots

4

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt


5

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

“A robot is a reprogrammable, multifunctional manipulator
designed to move material, parts, tools, or specialized devices
through variable programmed motions for the performance of
a variety of tasks.” (Robot Institute of America)

Definition:

Alternate definition:


A robot is a one
-
armed, blind idiot with limited memory and
which cannot speak, see, or hear.”

What is a robot?

6

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

What are robots good at?


What is hard for humans is easy for robots.


Repetitive tasks.


Continuous operation.


Complicated calculations.


Refer to huge databases.


What is easy for a human is hard for robots.


Reasoning.


Adapting to new situations.


Flexible to changing requirements.


Integrating multiple sensors.


Resolving conflicting data.


Synthesizing unrelated information.


Creativity.

7

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

What tasks would you give robots?


Dangerous


space exploration


chemical spill cleanup


disarming bombs


disaster cleanup


Boring and/or repetitive


welding car frames


part pick and place


manufacturing parts.


High precision or high speed


electronics testing


surgery


precision machining.

8

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Categories of Robots


Manipulators


Anchored somewhere: factory assembly lines, International
Space Station, hospitals.


Common industrial robots


Mobile Robots


Move around environment


UGVs, UAVs, AUVs, UUVs


Mars rovers, delivery bots, ocean explorers


Mobile Manipulators


Both move and manipulate


Packbot, humanoid robots

9

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

What subsystems make up a robot?


Sensors


Stationary base


Mobile


Actuators


Control/Software

Robert Stengel, Princeton Univ.

10

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Sensors


Perceive the world


Passive sensors capture signals generated by environment.
Background, lower power. E.G.: cameras.


Active sensors probe the environment. Explicitly triggered,
more info, higher power consumption. E.G. sonar


What are they sensing


The environment: e.g. range finders, obstacle detection


The robot’s location: e.g., gps, wireless stations


Robot’s own internals:
proprioceptive

sensors. e.g.: shaft
decoders


Stop and think about that one for a moment. Close your eyes
-

where’s your hand? Move it
-

where is it now?

11

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

What use are sensors?


Uses sensors for
feedback


Closed
-
loop robots use sensors in
conjunction with actuators to gain
higher accuracy


servo motors.



Uses include mobile robotics,
telepresence, search and rescue,
pick and place with machine
vision, anything involving human
interaction

12

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Some typical sensors


Optical


Laser / radar


3D


Color spectrum


Pressure


Temperature


Chemical


Motion & Accelerometer


Acoustic


Ultrasonic


E
-
field Sensing

13

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Effectors


Take some kind of action in the world


Involve movement of robot or
subcomponent of robot


Robot actions could include


Pick and place: Move items between points


Continuous path control: Move along a programmable
path


Sensory: Employ sensors for feedback (e
-
field
sensing)

14

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Some kinds of Actuators


Actuators


pneumatic


hydraulic


electric solenoid


Motors


Analog (continuous)


Stepping (discrete increments)


Gears, belts, screws, levers


15

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Mobility


Legs


Wheels


Tracks


Crawls


Rolls

16

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt


Simple joints (2D)


Translation/Prismatic


sliding
along one axis


square cylinder in square tube


Rotation.Revolute


rotating about
one axis


Compound joints (3D)


ball and socket = 3 revolute joints


round cylinder in tube = 1 prismatic,
1 revolute

How do robots move?

17

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Degrees of Freedom (DOF)


Degrees of freedom = Number of independent directions a
robot or its manipulator can move


3 degrees of freedom: 2 translation, 1 rotation


6 degrees of freedom: 3 translation, 3 rotation


How many degrees of freedom does your knee have?
Your elbow?


Effective DOF vs controllable DOF:


Underwater explorer might have up or down, left or
right, rolling. 3 controllable DOF.


Position includes x,y,z coordinates,
yaw, roll, pitch
.
(together the pose or kinematic state). 6 effective
DOF.


Holonomic: effective DOF = controllable DOF.

18

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Control
-

the Brain



Open loop, i.e., no feedback,
deterministic



Instructions


Rules


Closed loop, i.e., feedback


Learn


Adapt

19

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

What are some problems with control of robot
actions?


Joint play, compounded through N joints.


Accelerating masses produce vibration, elastic
deformations in links.


Torques, stresses transmitted depending on end
actuator loads.


Feedback loop creates instabilities.


Delay between sensing and reaction.


Firmware and software problems


Especially with more intelligent approaches

20

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Robotic Perception


Sensing isn’t enough: need to act on data sensed


Hard because data are noisy; environment is
dynamic and partially observable.


Must be mapped into an internal representation


state estimation


Good representations


contain enough information for good decisions


structured for efficient updating


natural mapping between representation and real world.

21

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Belief State


Belief state: model of the state of the
environment (including the robot)


X: set of variables describing the environment


X
t
: state at time t


Z
t
: observation received at time t


A
t
: action taken after Zt is observed


After A
t
, compute new belief state X
t+1


Probabilistic, because uncertainty in both X
t

and
Z
t
.

22

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Some Perception Problems


Localization: where is the robot, where are other
things in the environment


landmarks


range scans


Mapping: no map given, robot must determine
both environment and position.


SLAM: Simultaneous localization and mapping


Probabilistic approaches typical, but
cumbersome

23

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Software Architectures


Low
-
level, reactive control


bottom
-
up, sensor results directly trigger
actions


Model
-
based, deliberative planning


top
-
down, actions are triggered based on
planning around a state model

24

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Low
-
Level, Reactive Control


Augmented finite state machines


Sensed inputs and a clock determine next state


Build bottom up, from individual motions


Subsumption architecture synchronizes AFSMs,
combines values from separate AFSMs.


Advantages: simple to develop, fast


Disadvantages: Fragile for bad sensor data, don’t
support integration of complex data over time.


Typically used for simple tasks, like following a wall or
moving a leg.

25

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Model
-
Based Deliberative Planning


Belief State model


Current State, Goal State


Any of planning techniques


Typically use probabilistic methods


Advantages: can handle uncertain measurements and complex
integrations, can be responsive to change or problems.


Disadvantages: slow; current algorithms can take minutes.
Developing models for the number of actions involved in
driving a complex robot too cumbersome.


Typically used for high
-
level actions such as whether to move
and in which direction.

26

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Hybrid Architectures


Usually, actually doing anything requires both
reactive and deliberative processing.


Typical architecture is three
-
layer:


Reactive Layer: low
-
level control, tight senso
-
action
loop, decision cycle of milliseconds


Deliberative layer: global solutions to complex tasks,
model
-
based planning, decision cycle of minutes


Executive layer: glue. Accepts directions from
deliberative layer, sequences actions for reactive layer,
decision cycle of a second

27

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

How do you measures of performance of
robot?


Speed and acceleration


Resolution


Working volume


Accuracy


Cost


Plus all the kinds of evaluation functions we have
talked about for any AI system.

28

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Measures of Performance


Speed and acceleration


Faster speed often reduces resolution or increases cost


Varies depending on position, load.


Speed can be limited by the task the robot performs (welding,
cutting)


Resolution


Often a speed tradeoff


The smallest movement the robot can make


Working volume


The space within which the robot operates.


Larger volume costs more but can increase the capabilities of a
robot

29

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Where are robots working
now?


Healthcare and personal care


surgical aids, intelligent walkers, eldercare


Personal services


Roomba! Information kiosks, lawn mowers, golf
caddies, museum guides


Entertainment


sports (robotic soccer)


Human augmentation


walking machines, exoskeletons, robotic hands, etc.

30

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

And more...


Industry and Agriculture


assembly, welding, painting,
harvesting, mining, pick
-
and
-
place, packaging, inspection,
...


Transportation


Autonomous helicopters, pilot
assistance, materials
movement


Cars (DARPA Grand
Challenge, Urban Challenge)


Antilock brakes, lane
following, collision detection


Exploration and Hazardous
environments


Mars rovers, search and rescue,
underwater and mine exploration,
mine detection


Military


Reconnaissance, sentry, S&R,
combat, EOD


Household


Cleaning, mopping, ironing,
tending bar, entertainment,
telepresence/surveillance

31

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Tomorrow’s problems


Mechanisms


Morphology: What should robots look like?


Novel actuators/sensors


Estimation and Learning


Reinforcement Learning


Graphical Models


Learning by Demonstration


Manipulation (grasping)


What does the far side of an object look like? How
heavy is it? How hard should it be gripped? How can
it rotate? Regrasping?

32

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

And more...


Medical robotics


Autonomous surgery


Eldercare


Biological Robots


Biomimetic robots


Neurobotics


Navigation


Collision avoidance


SLAM/Exploration

33

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Self
-
X Robots


Self
-
feeding


Literally


Electrically


Self
-
replicating


Self
-
repairing


Self
-
assembly


Self
-
organization


Self
-
reconfiguration

34

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Human
-
Robot Interaction


Social robots


In care contexts


In home contexts


In industrial contexts


Comprehension


Natural language


Grounded knowledge acquisition


Roomba: “Uh
-
oh”

For example...

35

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Human
-
Robot Interaction


Social robots


Safety/security


Ubiquitous Robotics


Small, special
-
purpose robots

36

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

More Human
-
Robot Interaction


How do
humans

handle it?


Assumptions about retention and understanding


Anthropomorphization


How do robots make it easier?


Apologize
vs.

back off


Convey intent


Cultural context (implicit

vs. explicit

communication)

37

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

The Future of Robotics.


Robots that can learn.


Robots with artificial intelligence.


Robots that make other robots.


Swarms

38

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Some good robotics videos.


Swimming fish:


http://vger.aa.washington.edu/research.html


http://www.newscientist.com/article/dn14101
-
shoal
-
of
-
robot
-
fish
-
casts
-
a
-
wider
-
data
-
net.html


Robot wars:


http://robogames.net/videos.php


Japanese robots:


http://www.ecst.csuchico.edu/~renner/Teaching/Robotics/videos.html

(note: about half the
links are broken)


Social robots:


http://www.ai.mit.edu/projects/humanoid
-
robotics
-
group/kismet/kismet.html


Miscellaneous Robots:


http://www.newscientist.com/article/dn9972
-
video
-
top
-
10
-
robots.html


http://grinding.be/category/robots


Swarms


http://www.youtube.com/watch?v=SkvpEfAPXn4

39

CSC 8520 Spring 2010. Paula Matuszek

Slides based in part on www.jhu.edu/virtlab/course
-
info/ei/ppt/robotics
-
part1.ppt and
-
part2.ppt

Will robots take over the world?


Which decisions can the machine
make without human supervision?


May machine
-
intelligent systems
make mistakes (at the same level as
humans)?


May intelligent systems gamble
when uncertain (as humans do)?


Can (or should) intelligent systems
exhibit personality?


Can (or should) intelligent systems
express emotion?


How much information should the
machine display to the human
operator?

HAL
-

2001
Space Odyssey