Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 1

4 The Reactive Paradigm• Describe the Reactive Paradigm in terms of the 3 robot primitives

and its organization of sensing

• List the characteristics of a reactive robotic system, and discuss the connotations of surrounding the reactive paradigm

• Describe the two dominant methods for combining behaviors in a reactive architecture: subsumption and potential field summation

• Evaluate subsumption and pfield architectures in terms of: support for modularity, niche targetability, ease of portability to other domains, robustness

• Be able to program a behavior using pfields

• Be able to construct a new potential field from primitive pfields and sum pfields to generate an emergent behavior

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 2

4 Review: Lessons from Biology

• Programs should decompose complex actions into behaviors. Complexity emerges from concurrent behaviors acting independently

• Agents should rely on straightforward activation mechanisms such as IRM

• Perception filters sensing and considers only what is relevant to the task (action-oriented perception)

• Behaviors are independent but the output may be used in many ways including: combined with others to produce a resultant output or to inhibit others

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 3

4 Hierarchical Organization is“Horizontal”

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 4

4 More Biological is “Vertical”

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 5

4 Sensing is Behavior-Specific or Local

Behaviors can “share” perception without knowing itThis is behavioral sensor fusion

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 6

4 Subsumption:Rodney Brooks

From http://www.spe.sony.com/classics/fastcheap/index.html

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 7

4 Subsumption Philosophy• Modules should be grouped into

layers of competence

• Modules in a higher lever can override or subsume behaviors in the next lower level

– Suppression: substitute input going to a module

– Inhibit: turn off output from a module

• No internal state in the sense of a local, persistent representation similar to a world model.

• Architecture should be taskable: accomplished by a higher level turning on/off lower layers

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 8

4 Level 0: Runaway

HALT

COLLIDE

PS MS

RUN AWAYPS MS

runaway 0

wander 1 follow-corridor 2

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 9

4 Example Perception: Polar Plot

• Plot is ego-centric

• Plot is distributed (available to whatever wants to use it)

• Although it is a representation in the sense of being a data structure, there is no memory (contains latest information) and no reasoning (2-3 means a “wall”)

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

if sensing is ego-centric, canoften eliminate need for memory, representation

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 10

4 Level 1: Wander

runaway 0

wander 1 follow-corridor 2

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

encoders

AVOID

PS

MS

WANDER

PS MS

Note sharing ofPerception, fusion

What wouldInhibition do?

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 11

4 Class Exercise

runaway 0

wander 1 move2light 2

LIGHTPHOTO-

TROPHISM

S

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 12

4 Level 2: Follow-Corridors

runaway 0

wander 1 follow-corridor 2

STAY-IN-MIDDLE

PS MSReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 13

4 Subsumption Review

• What is the Reactive Paradigm in terms of primitives?

• What is the Reactive Paradigm in terms of sensing?

• Does the Reactive Paradigm solve the Open World problem?

• How does the Reactive Paradigm eliminate the frame problem?

• What is the difference between a behavior and a level of competence?

• What is the difference between suppression and inhibition in subsumption?

ReviewOrganization-SA-beh. specificSubsumption-Philosophy-Level 0-Level 1-Level 2Summary

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 14

4 Potential Fields:Ron Arkin

From http://www.cc.gatech.edu/aimosaic/faculty/arkin

From http://www.cc.gatech.edu/aimosaic/robot-lab/MRLhome.html

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 15

4 Potential Fields Philosophy• The motor schema component of a behavior can be

expressed with a potential fields methodology– A potential field can be a “primitive” or constructed from

primitives which are summed together– The output of behaviors are combined using vector summation

• From each behavior, the robot “feels” a vector or force– Magnitude = force, strength of stimulus, or velocity– Direction

• But we visualize the “force” as a field, where every point in space represents the vector that it would feel if it were at that point

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 16

4 Example: Run Away via Repulsion

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 17

4 5 Primitive Potential Fields

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 18

4 Common fields in behaviors

• Uniform– Move in a particular direction, corridor following

• Repulsion– Runaway (obstacle avoidance)

• Attraction– Move to goal

• Perpendicular– Corridor following

• Tangential– Move through door, docking (in combination with other fields)

• random– do you think this is a potential field? what would it look like?

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 19

4 Class Exercise

• Name the field you’d use for – Moving towards a light

– Avoiding obstacles

Attractive

Repulsive

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 20

4 Magnitude profiles

• Constant magnitude• linear drop off• exponential drop off

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 21

4 Combining Fields forEmergent Behavior

obstacleobstacle

goal

If robot were dropped anywhere on this grid,it would want to move to goal and avoid obstacle:

Behavior 1: MOVE2GOALBehavior 2: RUNAWAY

The output of each independent behavior is a vector,the 2 vectors is summed to produce emergent behavior

obstacle

goal

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 22

4

Note: In this example, repulsive field only extends for 2 meters;the robot runs away only if obstacle within2 meters

Note: in this example, robot can sense thegoal from 10 meters away

Fields and Their Combination

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 23

4 Path Taken

• If robot started at this location, it would take the following path

• It would only “feel”the vector for the location, then move accordingly, “feel” the next vector, move, etc.

• Pfield visualization allows us to see the vectors at all points, but robot never computes the “field of vectors” just the local vector

Robot only feels vectors for this

point when it (if) reaches that point

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 24

4 Example: follow-corridor or follow-sidewalk

Perpendicular Uniform

Combined

Note use of Magnitude profiles:Perpendicular decreases

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 25

4 Class Exercise:Draw Fields for Wall-Following(assume that robot stands still if no wall)

Just half of a follow-corridor, but…

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 26

4 But how does the robot see a wall without reasoning or intermediate

representations?

• Perceptual schema “connects the dots”, returns relative orientation

PS:Find-wall

MS: Perp.

MS: UniformS

Sonars

orientation

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 27

4 OK, But why isn’t that a representation of a wall?

• It’s not really reasoning that it’s a wall, rather it is reacting to the stimulus which happens to be smoothed (common in neighboring neurons)

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 28

4 Level 0: Runaway

Note: multiple instances ofa behavior vs. 1:Could just have 1 Instance of RUN AWAY,Which picks nearest reading;Doesn’t matter, but thisAllows addition of anotherSonar without changing theRUN AWAY behavior

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 29

4 Level 1: Wander

Wander isUniform, but

Changes directionaperiodically

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 30

4 Level 2: Follow Corridor

Follow-corridor

Should weLeaveRun AwayIn? Do weNeed it?

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 31

4 Pfields

• Advantages– Easy to visualize

– Easy to build up software libraries

– Fields can be parameterized

– Combination mechanism is fixed, tweaked with gains

• Disadvantages– Local minima problem (sum to magnitude=0)

• Box canyon problem

– Jerky motion

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 32

4 Example: Docking Behavior

•Arkin and Murphy, 1990, Questa, Grossmann, Sandini, 1995, Tse and Luo, 1998, Vandorpe, Xu, Van Brussel, 1995. Roth, Schilling, 1998, Santos-Victor, Sandini, 1997

Orientation, ratio of pixel counts tangent vectorTotal count attraction vector

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 33

4 Docking Behavior Video

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 34

4 Comparison of Architectures

• Similar in philosophy and results; essentially equivalent

• Support for modularity– Both decompose task into behaviors

– Subsumption favors hardware, pfields pure software• could do with just rules but lose modularity, design discipline

• Niche targetability – High; philosophy is to fit an ecological niche!

• Ease of portability to other domains– Only to ones that can be done with reflexive behaviors

– Subsumption not as easy with upper levels

• Robustness– Subsumption has implicit graceful degradation

Introduction to AI Robotics (MIT Press) Chapter 4: The Reactive Paradigm 35

4 Pfields Summary• Reactive Paradigm: SA, sensing is local

– Solves the Open World problem by emulating biology

– Eliminates the frame problem by not using any global or persistent representation

– Perception is direct, ego-centric, and distributed

• Two architectural styles are: subsumption and pfields

• Behaviors in pfield methodologies are a tight coupling of sensing to acting; modules are mapped to schemas conceptually

• Potential fields and subsumption are logically equivalent but different implementations

• Pfield problems include– local minima (ways around this)

– jerky motion

– bit of an art