4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm1 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 Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm2 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 Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm3 Hierarchical Organization is “Horizontal” Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm4 More Biological is “Vertical” Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm5 Sensing is Behavior-Specific or Local Behaviors can “share” perception without knowing it This is behavioral sensor fusion Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm6 Subsumption: Rodney Brooks From Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm7 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 Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm8 Level 0: Runaway HALT COLLIDE PS MS RUN AWAY PS MS runaway 0 wander 1 follow-corridor 2 Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm9 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”) Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary if sensing is ego-centric, can often eliminate need for memory, representation

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm10 Level 1: Wander runaway 0 wander 1 follow-corridor 2 Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary encoders AVOID PS MS WANDER PSMS Note sharing of Perception, fusion What would Inhibition do?

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm11 Class Exercise runaway 0 wander 1 move2light 2 LIGHT PHOTO- TROPHISM S Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm12 Level 2: Follow-Corridors runaway 0 wander 1 follow-corridor 2 STAY-IN-MIDDLE PSMS Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm13 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? Review Organization -SA -beh. specific Subsumption -Philosophy -Level 0 -Level 1 -Level 2 Summary

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm14 Potential Fields: Ron Arkin From From

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm15 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

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm16 Example: Run Away via Repulsion

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm17 5 Primitive Potential Fields

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm18 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?

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm19 Class Exercise Name the field you’d use for –Moving towards a light –Avoiding obstacles Attractive Repulsive

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm20 Magnitude profiles Constant magnitude linear drop off exponential drop off

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm21 Combining Fields for Emergent Behavior obstacle goal 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 obstacle goal

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm22 Note: In this example, repulsive field only extends for 2 meters; the robot runs away only if obstacle within 2 meters Note: in this example, robot can sense the goal from 10 meters away Fields and Their Combination

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm23 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

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm24 Example: follow-corridor or follow-sidewalk PerpendicularUniform Combined Note use of Magnitude profiles: Perpendicular decreases

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm25 Class Exercise: Draw Fields for Wall-Following (assume that robot stands still if no wall) Just half of a follow-corridor, but…

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm26 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: Uniform S Sonars orientation

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm27 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)

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm28 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

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm29 Level 1: Wander Wander is Uniform, but Changes direction aperiodically

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm30 Level 2: Follow Corridor Follow-corridor Should we Leave Run Away In? Do we Need it?

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm31 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

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm32 Example: Docking Behavior Arkin and Murphy, 1990, Questa, Grossmann, Sandini, 1995, Tse and Luo, 1998, Vandorpe, Xu, Van Brussel, Roth, Schilling, 1998, Santos-Victor, Sandini, 1997 Orientation, ratio of pixel counts  tangent vector Total count  attraction vector

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm33 Docking Behavior Video

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm34 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

4 Introduction to AI Robotics (MIT Press)Chapter 4: The Reactive Paradigm35 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