4
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
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
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
1
4
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
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
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
2
4
Hierarchical Organization is
“Horizontal”
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
3
4
More Biological is “Vertical”
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
4
4
Sensing is
Behavior-Specific or Local
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
Behaviors can “share” perception without knowing it
This is behavioral sensor fusion
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
5
4
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
Introduction to AI Robotics (MIT Press)
Subsumption:
Rodney Brooks
From http://www.spe.sony.com/classics/fastcheap/index.html
Chapter 4: The Reactive Paradigm
6
4
Subsumption Philosophy
•
Modules should be grouped into
layers of competence
Review
•
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
•
-Level 2
Summary
Modules in a higher lever can
override or subsume behaviors in
the next lower level
•
Architecture should be taskable:
accomplished by a higher level
turning on/off lower layers
– 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.
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
7
4
Level 0: Runaway
follow-corridor 2
wander 1
runaway 0
RUN AWAY
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
PS
MS
PS
MS
HALT
COLLIDE
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
8
4
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
Example Perception: Polar Plot
if sensing is ego-centric, can
often eliminate need for
memory, representation
• 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”)
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
9
4
Level 1: Wander
follow-corridor 2
wander 1
runaway 0
WANDER
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
PS
MS
AVOID
MS
encoders
What would
Inhibition do?
PS
Note sharing of
Perception, fusion
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
10
4
Class Exercise
move2light 2
wander 1
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
runaway 0
LIGHT
PHOTOTROPHISM
Introduction to AI Robotics (MIT Press)
S
Chapter 4: The Reactive Paradigm
11
4 Level 2: Follow-Corridors
STAY-IN-MIDDLE
PS
MS
follow-corridor 2
wander 1
runaway 0
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
12
4
Review
Organization
-SA
-beh. specific
Subsumption
-Philosophy
-Level 0
-Level 1
-Level 2
Summary
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?
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
13
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
14
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
15
4
Example: Run Away via Repulsion
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
16
4
5 Primitive Potential Fields
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
17
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
18
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
19
4
Magnitude profiles
• Constant magnitude
• linear drop off
• exponential drop off
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
20
4
Combining Fields for
Emergent Behavior
goal
goal
obstacle
obstacle
obstacle
If robot were dropped anywhere on this grid,
it would want to move to goal and avoid obstacle:
Behavior 1: MOVE2GOAL
Behavior 2: RUNAWAY
The output of each independent behavior is a vector,
the 2 vectors is summed to produce emergent behavior
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
21
4
Fields and Their Combination
Note: inrepulsive
this example,
robot
canforsense
the
Note: In this example,
field only
extends
2 meters;
meterswithin
away
the robot runsgoal
awayfrom
only 10
if obstacle
2 meters
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
22
4
Path Taken
Robot only feels
vectors for this
point when it (if)
reaches that point
• 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
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
23
4
Example: follow-corridor or
follow-sidewalk
Perpendicular
Uniform
Note use of
Magnitude profiles:
Perpendicular decreases
Combined
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
24
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
25
But how does the robot see a wall
without reasoning or intermediate
representations?
4
•
Perceptual schema “connects the dots”, returns relative orientation
PS:
Find-wall
Sonars
Introduction to AI Robotics (MIT Press)
orientation
MS: Perp.
S
MS: Uniform
Chapter 4: The Reactive Paradigm
26
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
27
4
Level 0: Runaway
Note: multiple instances of
a behavior vs. 1:
Could just have 1
Instance of RUN AWAY,
Which picks nearest reading;
Doesn’t matter, but this
Allows addition of another
Sonar without changing the
RUN AWAY behavior
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
28
4
Level 1: Wander
Wander is
Uniform, but
Changes direction
aperiodically
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
29
4
Level 2: Follow Corridor
Follow-corridor
Should we
Leave
Run Away
In? Do we
Need it?
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
30
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
31
4
Example: Docking Behavior
Orientation, ratio of
pixel counts 
tangent vector
Total count 
attraction vector
Introduction to AI Robotics (MIT Press)
•Arkin and Murphy, 1990, Questa,
Grossmann, Sandini, 1995, Tse and
Luo, 1998, Vandorpe, Xu, Van
Brussel, 1995. Roth, Schilling, 1998,
Chapter 4: The Reactive Paradigm
32
Santos-Victor, Sandini, 1997
4
Docking Behavior Video
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
33
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
34
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
Introduction to AI Robotics (MIT Press)
Chapter 4: The Reactive Paradigm
35