2. Topics: Introduction to Robotics CS 491/691(X) Lecture 8 Instructor: Monica Nicolescu

3. CS 491/691(X) - Lecture 82 Review Control Architectures Languages for robot control Computability Organizing principles Architecture selection criteria Reactive control

4. CS 491/691(X) - Lecture 83 Reactive Control Reactive control is based on tight (feedback) loops connecting a robot's sensors with its effectors Purely reactive systems do not use any internal representations of the environment, and do not look ahead –They work on a short time-scale and react to the current sensory information Reactive systems use minimal, if any, state information

5. CS 491/691(X) - Lecture 84 Collections of Rules Reactive systems consist of collections of reactive rules that map specific situations to specific actions Analog to stimulus-response, reflexes –Bypassing the “brain” allows reflexes to be very fast Rules are running concurrently and in parallel Situations –Are extracted directly from sensory input Actions –Are the responses of the system (behaviors)

6. CS 491/691(X) - Lecture 85 Mutually Exclusive Situations If the set of situations is mutually exclusive:  only one situation can be met at a given time  only one action can be activated Often is difficult to split up the situations this way To have mutually exclusive situations the controller must encode rules for all possible sensory combinations, from all sensors This space grows exponentially with the number of sensors

7. CS 491/691(X) - Lecture 86 Complete Control Space The entire state space of the robot consists of all possible combinations of the internal and external states A complete mapping from these states to actions is needed such that the robot can respond to all possibilities This is would be a tedious job and would result in a very large look-up table that takes a long time to search Reactive systems use parallel concurrent reactive rules  parallel architecture, multi-tasking

8. CS 491/691(X) - Lecture 87 Incomplete Mappings In general, complete mappings are not used in hand- designed reactive systems The most important situations trigger the appropriate reactions Default responses are used to cover all other cases E.g.: a reactive safe-navigation controller If left whisker bent then turn right If right whisker bent then turn left If both whiskers bent then back up and turn left Otherwise, keep going

9. CS 491/691(X) - Lecture 88 Action Selection If the rules are not triggered by unique mutually- exclusive conditions, more than one rule can be triggered at the same time  Two or more different commands are sent to the actuators Deciding which action to take is called action selection Arbitration: decide among multiple actions or behaviors Fusion: combine multiple actions to produce a single command

10. CS 491/691(X) - Lecture 89 Arbitration There are many different types of arbitration Arbitration can be done based on: a fixed priority hierarchy –rules have pre-assigned priorities a dynamic hierarchy –rules priorities change at run-time learning –rule priorities may be initialized and are learned at run- time, once or continuously

11. CS 491/691(X) - Lecture 810 Multi-Tasking Arbitration decides which one action to execute To respond to any rule that might become triggered all rules have to be monitored in parallel, and concurrently If no obstacle in front  move forward If obstacle in front  stop and turn away Wait for 30 seconds, then turn in a random direction Monitoring sensors in sequence may lead to missing important events, or failing to react in real time Reactive systems must support parallelism –The underlying programming language must have multi- tasking abilities

12. CS 491/691(X) - Lecture 811 Designing Reactive Systems How to can we put together multiple (large number) of rules to produce effective, reliable and goal directed behavior? How do we organize a reactive controller in a principled way? The best known reactive architecture is the Subsumption Architecture (Rod Brooks, MIT, 1985)

13. CS 491/691(X) - Lecture 812 Vertical v. Horizontal Systems Traditional (SPA): sense – plan – act Subsumption:

14. CS 491/691(X) - Lecture 813 Biological Inspiration The inspiration behind the Subsumption Architecture is the evolutionary process : –New competencies are introduced based on existing ones Complete creatures are not thrown out and new ones created from scratch –Instead, solid, useful substrates are used to build up to more complex capabilities

15. CS 491/691(X) - Lecture 814 The Subsumption Architecture Principles of design –systems are built from the bottom up –components are task-achieving actions/behaviors (avoid-obstacles, find-doors, visit-rooms) –all rules can be executed in parallel, not in a sequence –components are organized in layers, from the bottom up –lowest layers handle most basic tasks –newly added components and layers exploit the existing ones

16. CS 491/691(X) - Lecture 815 Subsumption System Design What makes a Subsumption Layer, what should go where? There is no strict recipe, but some solutions are better than others, and most are derived empirically How exactly layers are split up depends on the specifics of the robot, the environment, and the task

17. CS 491/691(X) - Lecture 816 Designing in Subsumption Qualitatively specify the overall behavior needed for the task Decompose that into specific and independent behaviors (layers) Determine behavior granularity Ground low-level behaviors in the robot’s sensors and effectors Incrementally build, test, and add

18. CS 491/691(X) - Lecture 817 Subsumption Layers First, we design, implement and debug layer 0 Next, we design layer 1 –When layer 1 is designed, layer 0 is taken into consideration and utilized, its existence is subsumed (thus the name of the architecture) –As layer 1 is added, layer 0 continues to function Continue designing layers, until the desired task is achieved level 2 level 1 level 0 sensorsactuators

19. CS 491/691(X) - Lecture 818 Suppression and Inhibition Higher layers can disable the ones below –Avoid-obstacles can stop the robot from moving around Layer 2 can either: –Inhibit the output of level 1 or –Suppress the input of level 1 The process is continued all the way to the top level AFSM inputsoutputs suppressor inhibitor I s level 2 level 1 level 0 sensorsactuators

20. CS 491/691(X) - Lecture 819 Subsumption Language and AFSMs The original Subsumption Architecture was implemented using the Subsumption Language It was based on finite state machines (FSMs) augmented with a very small amount of state (AFSMs) AFSMs were implemented in Lisp AFSM inputsoutputs suppressor inhibitor I s

21. CS 491/691(X) - Lecture 820 Subsumption Language and AFSMs Each behavior is represented as an augmented finite state machine (AFSMs) Stimulus (input) or response (output) can be inhibited or suppressed by other active behaviors An AFSM can be in one state at a time, can receive one or more inputs, and send one or more outputs AFSMs are connected communication wires, which pass input and output messages between them; only the last message is kept AFSMs run asynchronously AFSM inputsoutputs suppressor inhibitor I s collide halt sonar

22. CS 491/691(X) - Lecture 821 Networks of AFSMs Layers represent task achieving behaviors –Wandering, avoidance, goal seeking Layers work concurrently and asynchronously A Subsumption Architecture controller, using the AFSM-based programming language, is a network of AFSMs divided into layers Convenient for incremental system design level 2 level 1 level 0

23. CS 491/691(X) - Lecture 822 Wandering in Subsumption Brooks ‘87

24. CS 491/691(X) - Lecture 823 Layering in AFSM Networks Once a basic competence is achieved (e.g., moving around safely ), it can be labeled as layer 0 Layer 1 (e.g., one that looks for objects and collects them ), can then be added on top and communication is done through wires The use of layers is meant to modularize the reactive system, so it is bad design to put a lot of behaviors within a single layer Also, it is bad design to put a large number of connections between the layers, so that they are strongly coupled

25. CS 491/691(X) - Lecture 824 Module Independence Strong coupling implies dependence between modules, which violates the modularity of the system If modules are interdependent, they are not as robust to failure In Subsumption, if higher layers fail, the lower ones remain unaffected Thus Subsumption has one-way independence between layers Two-way independence is not practical, why?

26. CS 491/691(X) - Lecture 825 Layering in AFSM Networks With upward independence, a higher layer can always use a lower one  layer 1 certainly can and should be coupled with layer 0. How? …by using suppression and inhibition Do we always have to use these wires to communicate between parts of the system?

27. CS 491/691(X) - Lecture 826 Using the World How can you sequence activities in Subsumption? Coupling between layers need not be through the system itself (i.e., not through explicit communication wires) It could be through the world. How?

28. CS 491/691(X) - Lecture 827 Collecting Soda Cans Herbert collected empty soda cans and took them home Herbert’s capabilities –Move around without running into obstacles –Detect soda cans using a camera and a laser –An arm that could: extend, sense if there is a can in the gripper, close the gripper, tuck the arm in

29. CS 491/691(X) - Lecture 828 Herbert Look for soda cans, when seeing one approach it When close, extend the arm toward the soda can If the gripper sensors detect something close the gripper If can is heavy, put it down, otherwise pick it up If gripper was closed tuck the arm in and head home The robot did not keep internal state about what it had just done and what it should do next: it just sensed!

30. CS 491/691(X) - Lecture 829 Readings M. Matarić: Chapter 14