1 / 33

The Reactive Paradigm

Introduction to Intelligent Robots. The Reactive Paradigm. Embedded System Lab Kim Jong Hwi. Chapter Objectives Define what the reactive paradigm List the characteristics of a reactive robotic system

starbuck
Télécharger la présentation

The Reactive Paradigm

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Introduction to Intelligent Robots The Reactive Paradigm • Embedded System Lab • Kim JongHwi Chonbuk National University

  2. Chapter Objectives • Define what the reactive paradigm • List the characteristics of a reactive robotic system • Describe the two dominant methods for combining behaviors in a reactive architecture: subsumption and potential field summation • Be able to program a behavior using a potential field methodology • Be able to construct a new potential field form primitive potential fields, and sum potential fields to generate an emergent behavior Chonbuk National University

  3. Reactive Paradigm - Overview Subsumption Architecture Potential Field Methodologies Pros and cons Summary Chonbuk National University

  4. The Reactive Paradigm • emerged in the late 1980’s • grew out of dissatisfaction with the hierarchical paradigm • -summarized by Roney Brooks Chonbuk National University

  5. The Reactive Paradigm • layered in a vertical decomposition • access to sensors and actuators independently Chonbuk National University

  6. Attributes of Reactive Paradigm • all actions are accomplished through behaviors • motor schema : algorithm for generating the pattern of action in physical actuator • perceptual schema : algorithm for extracting the percept and its strength Chonbuk National University

  7. S-A organization Chonbuk National University

  8. Behavior-specific sensing organization in the Reactive Paradigm Chonbuk National University

  9. Connotations of reactive behaviors • executes rapidly • have no memory Chonbuk National University

  10. 5 Characteristics of reactive behaviors • Robots are situated agents operating in an ecological niche • Behaviors serve as the basic building blocks for robotic actions, and the overall behavior of the robot is emergent • Only local, behavior-specific sensing is permitted • These systems inherently follow good software design principle • Animal models of behavior are often cited as a basis for these systems or a particular behavior Chonbuk National University

  11. Representative architectures • Subsumption – how behaviors are combined • Potential Field Methodologies – require behaviors to be implemented as potential fields and the behaviors are combined by summation of the fields • Rule encoding, fuzzy methods, winner-take-all voting … Chonbuk National University

  12. Subsumption architecture • Rodney Brooks’s architecture • the most influential of the purely Reactive Paradigm systems Chonbuk National University

  13. Subsumption architecture • Modules are grouped into layers of competence • (low layer ~ high layer) • Modules in a higher layer can override, or subsume, the output from behaviors in the next lower layer • The use of internal state is avoided • A task is accomplished by activating the appropriate layer Chonbuk National University

  14. Example Chonbuk National University

  15. Level 0 recast as primitive behaviors Chonbuk National University

  16. Level 1 : wander Chonbuk National University

  17. Level 1 recast as primitive behaviors Chonbuk National University

  18. Level 2 : follow corridors Chonbuk National University

  19. Potential Field • force field on the surrounding space exerted from perceivable objects • Vector • Magnitude; real number between 0.0 and 1 • Direction Chonbuk National University

  20. Potential Field Chonbuk National University

  21. Potential Field Chonbuk National University

  22. Programming a single potential Field Chonbuk National University

  23. Programming a single potential Field Chonbuk National University

  24. Programming a single potential Field Chonbuk National University

  25. Programming a single potential Field Chonbuk National University

  26. Programming a single potential Field Chonbuk National University

  27. Programming a single potential Field Chonbuk National University

  28. Programming a single potential Field Chonbuk National University

  29. Programming a single potential Field Chonbuk National University

  30. Programming a single potential Field Chonbuk National University

  31. Advantages and disadvantages • Advantages • easy to visualize over a large region of space • easier for the designer to visualize the robot’s overall behavior • easy to combine fields, and languages such as C++ • well works behaviors developed for 2D in 3D inviroment • Disadvantages • Local minima (vector with 0 magnitude) • producing vectors with a small magnitude from random noise • NaTs (navigation templates) Chonbuk National University

  32. Summary • subsumption and potential fields appear to be largely equivalent in practice • The ease of portability to other domains is relative to the complexity of the changes in the task and enviroment • Neither style of architecture explicitly addresses robustness Chonbuk National University

  33. Thank you for listening! Chonbuk National University

More Related