23
CS 415 – A.I. Slide Set 8

CS 415 – A.I

Embed Size (px)

DESCRIPTION

CS 415 – A.I. Slide Set 8. Agenda. Today Subsumption Architecture Wednesday Mapping Other Topics Emergent Knowledge Computer Vision Stochastic Learning Knowledge Representation Group Robotics. What kind of control?. Deliberative Control Think Hard, Act Later Reactive Control - PowerPoint PPT Presentation

Citation preview

Page 1: CS 415 – A.I

CS 415 – A.I.

Slide Set 8

Page 2: CS 415 – A.I

Agenda

• Today– Subsumption Architecture

• Wednesday–Mapping

• Other Topics– Emergent Knowledge– Computer Vision– Stochastic Learning– Knowledge Representation–Group Robotics

Page 3: CS 415 – A.I

What kind of control?

• Deliberative Control– Think Hard, Act Later

• Reactive Control– Don't Think, React

• Hybrid Control– Think Sometimes

• Behavior-Based Control Emergent Behavior

Page 4: CS 415 – A.I

Subsumption Architecture

• Brooks Paper-1985– One particular, popular way to generate reactive

control architectures

• Interesting Note– Rodney Brooks co-founded, and is Chief Technical

Officer and currently sits on the Board of iRobot corp.

Page 5: CS 415 – A.I

Possible Approaches

• Traditionally• Robotics Control was conceptualized linearly• Figure 1• Decompose problem into a series of functional units

– Subsumption Architecture• Robotics Control in Parallel• Figure 2• Revolutionary – Turn model on its end• Decompose problem into task achieving behaviors

Page 6: CS 415 – A.I

6

Let’s imagine a robot that cooks vegetables...

• Traditional AI robots

Colour, shape, odor, consistency...

Classification of items depending on the robot’s model :

Vegetable with peel or not, time needed to be cooked

Detection of dirtiness, texture sensors

Tasks planning to synchronized actions

Actions : wash or peel vegetables, put

it in a sauce pan until it is cooked.

Page 7: CS 415 – A.I

7

Let’s imagine a robot that cooks...

• Subsumption architecture robots

Preparing vegetable to be

cooked

Detection of dirtiness, texture sensors

Cook

Avoid from burning

Wash vegetable in water or peel it

Heat sensor, texture sensor, detection of

dirtiness

Smoke detection

Put vegetable in a sauce pan

Served vegetable

Page 8: CS 415 – A.I

Requirements• Multiple goals– Sometimes conflicting–Differing/changing relative importance

• Multiple sensors– Error prone, No direct relation to real world– Inconsistent Readings

• Robustness–Overcome failures• Processor, environment, sensors

• Extensibility

Page 9: CS 415 – A.I

Assumed Dogmas

• We want autonomous robots–Map making is crucial– The map should be 3D– Relative maps are better than global

• Complexity behavior doesn't assume complex design

• Keep things simple• Visual data is most desirable• Self-calibration and recovery– Self-sustaining artificial beings

Page 10: CS 415 – A.I

The Testbed

• Processing – offboard LISP• 3 parallel drive wheels• 12 Sonar (rotating body)• 2 CCD Cameras (tilt head)• On board processor – Intel 8031– 12K/sec Radio link

Page 11: CS 415 – A.I

Levels of Competence

• Traditional Approach– Slice problem according to internal workings of

solution

• Brooks Approach– Slice problem according to desired external

manifestation

• Level of Competence – informal specification of a desired class of behaviors for a robot over any and all environments

Page 12: CS 415 – A.I

Particular Levels

• 0 – Obstacle Avoidance• 1 – Wander aimlessly while avoiding• 2 – Explore (pick a destination)• 3 – Mapping• 4 – Notice changes in the environment• 5 – Reason about identified objects• 6 – Change the world somehow• 7 – Reason about behavior of objects/modify your plans• IMPORTANT – each higher level includes as a subset

previous layers

Page 13: CS 415 – A.I

Building the Controller

• Build an entire robot that realizes level 0 “perfectly”–Never change this level

• Build another layer (level 1) on top of level 0– Level 1 knows about, can examine data from and

can inject data into the data flow of level 0• Each higher level subsumes lower ones

–No level knows anything about levels above it

Page 14: CS 415 – A.I

Relating to our Goals• Multiple Goals – concurrent goal pursuit is

possible/beneficial–Don't need to decide ahead of time what goal to

pursue

• Multiple Sensors – don't need to enforce a central representation

• Robustness – Higher levels may be slower, but lower levels still run

• Extensibility – smarter and smarter higher levels

Page 15: CS 415 – A.I

Control System Spec. Lang• Each processor is a finite state machine.–Named states• NIL, reset,

– Types of States• Output, Side effect, Conditional dispatch, Event

dispatch• Multiple inputs/outputs– Can be suppressed/inhibited

• Example pg 10 and 11– LISP-like spec for avoid module– Schematic

Page 16: CS 415 – A.I

Early Implementations

• Level 0 and Level 1 (part of Level 2)– Evolving Schematics on pgs 11-16 show how the

subsumption architecture “evolves”

• Paper also describes a simulated robot implementing the theory where hardware could not (as of August 1985)

Page 17: CS 415 – A.I

• Since then, many subsumption architectures have been developed– Robot named Herbert• Designed by Jonathan Connell• Aluminum can collector

– Layer 2 was programmed to pick likely locations of empty cans– Layer N handled the gripping arm

Page 18: CS 415 – A.I

18

Packbot (2002)

• help clear caves and bunkers, search buildings and cross live anti-personnel minefields

• speed of up to 14 km/h

• continuous 360 degrees rotation

• negotiation of rough terrain and obstacles such as stairs, rocks, logs, rubble and debris.

• can climb grades up to 60%

• can survive submersion in water up to two meter deep

Page 19: CS 415 – A.I

19

R-gator (2006):

• The R-Gator Unmanned Vehicles for Physical Security pilot project:– Teleoperation – Autonomous waypoint navigation with “Teach & Playback” – Robotic following – Obstacle avoidance – Manual operation

Page 20: CS 415 – A.I

20

Planetary Rover

• A system suitable for a Mars Rover robot • Tasks

Move autonomously upon the rocky, cratered Martian surface

Gathering soil, atmospheric samples and images

• Difficulty No knowledge of the appearance of the

ground, the locations and the obstacles is available

Page 21: CS 415 – A.I

21

Mars Rovers

• R. Brooks and A. Flynn (1989), "Fast, cheap, and out of control: A robot invasion of the solar system," J. Brit. Interplanetary Soc., vol. 42, no. 10, pp. 478-485, 1989.–Mars Pathfinder–Mars Exploration Rovers• These still have human intervention, however, but not

much

Page 22: CS 415 – A.I

Problems in 1985

• Painfully slow processors• Very close link between code and hardware– Low level considerations were necessary • How many logic gates does this bit of LISP take

Page 23: CS 415 – A.I

Problems that are still applicable today?

• Any ideas?

• Scalability• Like hybrid control – what action do I do next?–What makes a good subsumption architecture?–What should the hierarchy look like?–Why are you worrying about it?

• How flexible is the design... really?