Autonomous Mobile Robots CPE 470/670 Lecture 10 Instructor: Monica Nicolescu

CPE 470/670 - Lecture 102 Review The Subsumption Architecture –Herbert, Genghis, The Nerd Herd, Tom and Jerry –Advantages and dissadvantages Behavior-based control –Definitions –Principles of behavior-based control –Toto: a behavior-based mapping robot

CPE 470/670 - Lecture 103 What Is a Behavior? Behavior-achieving modules Rules of implementation Behaviors achieve or maintain particular goals (homing, wall-following) Behaviors are time-extended processes Behaviors take inputs from sensors and from other behaviors and send outputs to actuators and other behaviors Behaviors are more complex than actions (stop, turn- right vs. follow-target, hide-from-light, find-mate etc.)

CPE 470/670 - Lecture 104 Principles of BBC Design Behaviors are executed in parallel, concurrently –Ability to react in real-time Networks of behaviors can store state (history), construct world models/representation and look into the future –Use representations to generate efficient behavior Behaviors operate on compatible time-scales –Ability to use a uniform structure and representation throughout the system

CPE 470/670 - Lecture 105 An Example Task: Mapping Design a robot that is capable of: –Moving around safely –Make a map of the environment –Use the map to find the shortest paths to particular places Navigation & mapping are the most common mobile robot tasks

CPE 470/670 - Lecture 106 Map Representation The map is distributed over different behaviors We connect parts of the map that are adjacent in the environment by connecting the behaviors that represent them The network of behaviors represents a network of locations in the environment Topological map: Toto (Matarić ’90)

CPE 470/670 - Lecture 107 Toto’s Controller

CPE 470/670 - Lecture 108 Landmark Detection Keep track of what was sensed and how it was moving –meandering  cluttered area –constant compass direction, go straight  left, right walls –moving straight, both walls  corridor

CPE 470/670 - Lecture 109 Building a Map Each landmark was stored in a behavior Whenever a new landmark was discovered a new behavior was added Adjacent landmarks are connected by communication wires This resulted in a topological representation of the environment, i.e., a topological world model

CPE 470/670 - Lecture 1010 Toto’s Mapping Behaviors Each landmark was stored in a behavior Each such landmark behavior stored (remembered) some information –landmark type (wall, corridor, irregular) –compass heading –approximate length/size –some odometry my-behavior-type: corridor my-compass-direction: NV my-approximate-location: x,y my-approximate-length: length whenever received (input) if input(behavior-type)= my-behavior-type and input (compass-direction) = my-compass-direction then active <- true

CPE 470/670 - Lecture 1011 Localization Whenever a landmark is detected, its description (type, compass direction, etc.) is sent to all behaviors in parallel  the one that matches becomes active When nothing in the map matches  a new place/landmark was discovered and added to the map If an existing behavior was activated, it inhibited any other active behaviors

CPE 470/670 - Lecture 1012 Getting Around Toto can use the map to navigate The behavior that corresponds to the goal sends messages (spreads activation) to all of its neighbors The neighbors send messages to their neighbors in turn So on, until the messages reach the currently active behavior This forms path(s) from the current state to the goal

CPE 470/670 - Lecture 1013 Path Following Toto did not keep a sequence of behaviors Instead, messages were passed continuously –Useful in changing environments How does Toto decide where to go if multiple choices are available? –Rely on the landmark size: behaviors add up their own length as messages are passed from one behavior to another  give path length –Choose the shortest path Thus, one behavior at a time, it reached the goal

CPE 470/670 - Lecture 1014 Toto - Video

CPE 470/670 - Lecture 1015 Expression of Behaviors Example: –Going from a classroom to another What does it involve? –Getting to the destination from the current location –Not bumping into obstacles along the way –Making your way around students on corridors –Deferring to elders –Coping with change in the environment

CPE 470/670 - Lecture 1016 Stimulus-Response Diagrams Behaviors are represented as a general response to a particular stimulus move-to-class avoid-object dodge-student stay-right defer-to-elder COORDINATORCOORDINATOR class location detected object detected student detected path detected elder Actions

CPE 470/670 - Lecture 1017 Finite State Acceptor Diagrams Useful for describing aggregations and sequences of behaviors Finite state acceptor: –Q: set of allowable behavioral states –  : transition function from (input, current state)  new state –q 0 : initial state –F: set of accepting (final) states StartJourney Lost At-class move error reached-class othernot-at-classall

CPE 470/670 - Lecture 1018 Formal Methods Have very useful properties for the programmer –Can be used to verify designer intentions –Provide a framework for formal analysis of the program, adequacy and completeness –Facilitate the automatic generation of control systems –Provide a common language for expressing robot behaviors –Provide support for high-level programming language design

CPE 470/670 - Lecture 1019 Situated Automata Kaelbling & Rosenschein (’91) Controllers are designed as logic circuits Capable of reasoning REX: Lisp-based language –First language to encode a reactive systems with synchronous digital circuitry Gapps: goals are specified more directly –Achievement, maintenance, execution –Logical boolean operators are used to create higher-level goals  generate circuits

CPE 470/670 - Lecture 1020 Situated Automata (defgoalr (ach in-classroom) (if (not start-up) (maint (and (maint move-to-classroom) (maint avoid-objects) (maint dodge-students) (maint stay-to-right-on-path) (maint defer-to-elders) )

CPE 470/670 - Lecture 1021 Discrete Behavioral Encoding The behavior consists of a set finite set of (situation, response) pairs Rule-based systems IF antecedent THEN consequent Condition-action production rules (Nilsson ’94) –Produce durative actions: “move at 5m/s” vs. “move 5 m” The Subsumption Architecture ( whenever condition & consequent) ( defbehavior name & inputs outputs declarations processes)

CPE 470/670 - Lecture 1022 Continuous Behavioral Encoding Continuous response provides a robot an infinite space of potential reactions to the world A mathematical function transforms the sensory input into a behavioral reaction Potential fields –Law of universal gravitation: potential force drops off with the square of the distance between objects –Goals are attractors and obstacles are repulsors –Separate fields are used for each object –Fields are combined (superposition)  unique global field

CPE 470/670 - Lecture 1023 Potential Fields Ballistic goal attraction field Superposition of two fields

CPE 470/670 - Lecture 1024 Potential Fields Advantages –Provide an infinite set of possibilities of reaction –Highly parallelizable Disadvantages –Local minima, cyclic-oscillatory behavior –Apparently, large amount of time required to compute the entire field: reaction is computed only at the robot’s position!

CPE 470/670 - Lecture 1025 Motor Schemas Motor schemas are a type of behavior encoding – Based on neuroscience and cognitive science They are based on schema theory (Arbib) –Explains motor behavior in terms of the concurrent control of many different activities –Schemas store how to react and the way the reaction can be realized: basic units of activity –Schema theory provides a formal language for connecting action and perception –Activation levels are associated with schemas, and determine their applicability for acting

CPE 470/670 - Lecture 1026 Visually Guided Behaviors Michael Arbib & colleagues constructed computer models of visually guided behaviors in frogs and toads Toads & frogs respond visually to –Small moving objects  feeding behavior –Large moving objects  fleeing behavior Behaviors implemented as a vector field (schemas) –Attractive force (vector) along the direction of the fly What happens when presented with two files simultaneously? –The frog sums up the two vectors and snaps between the two files, missing both of them

CPE 470/670 - Lecture 1027 Motor Schemas Provide large grain modularity Schemas act concurrently, in a cooperative but competing manner Schemas are primitives from which more complex behaviors ( assemblages can be constructed) Represented as vector fields

CPE 470/670 - Lecture 1028 Examples of Schemas Obstacle avoid and stay on corridor schemas

CPE 470/670 - Lecture 1029 Schema Representation Responses represented in uniform vector format Combination through cooperative coordination via vector summation No predefined schema hierarchy Arbitration is not used –each behavior has its contribution to the robot’s overall response –gain values control behavioral strengths Here is how:

CPE 470/670 - Lecture 1030 The Role of Gains in Schemas Low gain High gain

CPE 470/670 - Lecture 1031 Designing with Schemas Characterize motor behaviors needed Decompose to most primitive level, use biological guidelines where appropriate Develop formulas to express reaction Conduct simple simulations Determine perceptual needs to satisfy motor schema inputs Design specific perceptual algorithms Integrate/test/evaluate/iterate

CPE 470/670 - Lecture 1032 Foraging Example

CPE 470/670 - Lecture 1033 Strengths and Weaknesses Strengths: – support for parallelism – run-time flexibility – timeliness for development – support for modularity Weaknesses: –hardware retargetability –combination pitfalls (local minima, oscillations)

CPE 470/670 - Lecture 1034 Schema-Based Robots At Georgia Tech (Ron Arkin) Exploration Hall following Wall following Impatient waiting Navigation Docking Escape Forage

CPE 470/670 - Lecture 1035 Behavior Coordination Behavior-based systems require consistent coordination between the component behaviors for conflict resolution Coordination of behaviors can be: –Competitive: one behavior’s output is selected from multiple candidates –Cooperative: blend the output of multiple behaviors –Combination of the above two

CPE 470/670 - Lecture 1036 Competitive Coordination Arbitration: winner-take-all strategy  only one response chosen Behavioral prioritization –Subsumption Architecture Action selection/activation spreading (Pattie Maes) –Behaviors actively compete with each other –Each behavior has an activation level driven by the robot’s goals and sensory information Voting strategies (DAMN architecture, Rosenblatt) –Behaviors cast votes on potential responses

CPE 470/670 - Lecture 1037 The DAMN Architecture Distributed Architecture for Mobile Navigation (Rosenblatt 1995) Multi-valued behaviors (at all levels) propose multiple action preferences Each behavior votes for or against sets of actions Arbiter selects max weighted vote sum Practically demonstrated on real-world long-distance navigation Disadvantage: highly heuristic

CPE 470/670 - Lecture 1038 Cooperative Coordination Fusion: concurrently use the output of multiple behaviors Major difficulty in finding a uniform command representation amenable to fusion Fuzzy methods Formal methods –Potential fields –Motor schemas –Dynamical systems

CPE 470/670 - Lecture 1039 Emergent Behavior The resulting robot behavior may sometimes be surprising or unexpected  emergent behavior

CPE 470/670 - Lecture 1040 Wall Following A simple wall following controller: –If too close on left-back, turn left –If too close on left-front, turn right –Similarly for right –Otherwise, keep straight If the robot is placed close to a wall it will follow Is this emergent? –The robot has no explicit representations of walls –The controller does not specify anything explicit about following

CPE 470/670 - Lecture 1041 Emergence A “holistic” property, where the behavior of the robot is greater than the sum of its parts A property of a collection of interacting components –A robot’s interaction with the environment –The interaction of behaviors Often occurs in reactive and behavior-based systems (BBS) Typically exploited in reactive and BBS design

CPE 470/670 - Lecture 1042 Flocking How would you design a flocking behavior for a group of robots? Each robot can be programmed with the same behaviors: –Don’t get too close to other robots –Don’t get too far from other robots –Keep moving if you can When run in parallel these rules will result in the group of robots flocking

CPE 470/670 - Lecture 1043 Emergent Behavior Emergent behavior is structured behavior that is apparent at one level of the system (the observer’s point of view) and not apparent at another (the controller’s point of view) The robot generates interesting and useful behavior without explicitly being programmed to do so!! E.g.: Wall following can emerge from the interaction of the avoidance rules and the structure of the environment

CPE 470/670 - Lecture 1044 Components of Emergence The notion of emergence depends on two components –The existence of an external observer, to observe the emergent behavior and describe it –Access to the internals of the controller, to verify that the behavior is not explicitly specified in the system The combination of the two is, by many researchers, the definition of emergent behavior

CPE 470/670 - Lecture 1045 Unexpected & Emergent Behavior Some argue that the description above is not emergent behavior and that it is only a particular style of robot programming –Use of the environment and side-effects leads to the novel behavior Their view is that emergent behavior must be truly unexpected, and must come to a surprise to the external observer

CPE 470/670 - Lecture 1046 Expectation and Emergence The problem with unexpected surprise as property of behavior is that: –it entirely depends on the expectations of the observer which are completely subjective –it depends on the observer’s knowledge of the system (informed vs. naïve observer) –once observed, the behavior is no longer unexpected

CPE 470/670 - Lecture 1047 Emergent Behavior and Execution Emergent behavior cannot always be designed in advance and is indeed unexpected This happens as the system runs, and only at run-time can emergent behavior manifest itself The exact behavior of the system cannot be predicted –Would have to consider all possible sequences and combinations of actions in all possible environments –The real world is filled with uncertainty and dynamic properties –Perception is affected by noise If we could sense the world perfectly, accurate predictions could be made and emergence would not exist!

CPE 470/670 - Lecture 1048 Desirable/Undesirable Emergent Behavior New, unexpected behaviors will always occur in any complex systems interacting with the real world Not all behaviors (patterns, or structures) that emerge from the system's dynamics are desirable! Example: a robot with simple obstacle avoidance rules can oscillate and get stuck in a corner This is also emergent behavior, but regarded as a bug rather than a feature

CPE 470/670 - Lecture 1049 Sequential and Parallel Execution Emergent behavior can arise from interactions of the robot and the environment over time and/or over space Time-extended execution of behaviors and interaction with the environment (wall following) Parallel execution of multiple behaviors (flocking) Given the necessary structure in the environment and enough space and time, numerous emergent behaviors can arise

CPE 470/670 - Lecture 1050 Architectures and Emergence Different architectures have different methods for dealing with emergent behaviors: modularity directly affects emergence Reactive systems and behavior-based systems exploit emergent behavior by design –Use parallel rules and behaviors which interact with each other and the environment Deliberative systems and hybrid systems aim to minimize emergence –Sequential, no interactions between components, attempt to produce a uniform output of the system

CPE 470/670 - Lecture 1051 Readings M. Matarić: Chapters 17, 18