Page 122 - Introduction to AI Robotics
P. 122

4 The Reactive Paradigm








                                      Chapter Objectives:

                                        Define what the reactive paradigm is in terms of i) the three primitives
                                         SENSE, PLAN, and ACT, and ii) sensing organization.

                                        List the characteristics of a reactive robotic system, and discuss the con-
                                         notations surrounding the reactive paradigm.

                                        Describe the two dominant methods for combining behaviors in a reactive
                                         architecture: subsumption and potential field summation.
                                        Evaluate subsumption and potential fields architectures in terms of: sup-
                                         port for modularity, niche targetability, ease of portability to other domains, ro-
                                         bustness.
                                        Be able to program a behavior using a potential field methodology.

                                        Be able to construct a new potential field from primitive potential fields,
                                         and sum potential fields to generate an emergent behavior.


                                4.1   Overview

                                      This chapter will concentrate on an overview of the reactive paradigm and
                                      two representative architectures. The Reactive Paradigm emerged in the late
                                      1980’s. The Reactive Paradigm is important to study for at least two reasons.
                                      First, robotic systems in limited task domains are still being constructed us-
                                      ing reactive architectures. Second, the Reactive Paradigm will form the basis
                                      for the Hybrid Reactive-Deliberative Paradigm; everything covered here will
                                      be used (and expanded on) by the systems in Ch. 7.
   117   118   119   120   121   122   123   124   125   126   127