Page 342 - Introduction to AI Robotics
P. 342

9 Topological Path Planning








                                      Chapter Objectives:

                                        Define the difference between a natural and artificial landmark andgiveone
                                         example of each.
                                        Given a description of an indoor office environment and a set of behav-
                                         iors, build a relational graph representation labeling the distinctive places
                                         and local control strategies using gateways.
                                        Describe in one or two sentences: gateway, image signature, visual homing,
                                         viewframe, orientation region.

                                        Given a figure showing landmarks, create a topological map showing
                                         landmarks, landmark pair boundaries, and orientation regions.


                                9.1   Overview


                         TOPOLOGICAL  Topological, route,or qualitative navigation is often viewed as being more sim-
                          NAVIGATION  ple and natural for a behavior-based robot. Certainly people frequently give
                                      other people routes as directives; therefore it seems natural to expect a robot
                                      to be able to parse commands such as “go down the hall, turn to the left at
                                      the dead end, and enter the second room on the right.” Even without a map
                                      of where everything is, there is enough information for navigation as long as
                                      the robot knows what a “hall,” “dead-end,“ and “room” is.
                                        Route representations fall into one of two approaches:
                                      1. Relational. Relational techniques are the most popular, and can be thought
                                         of as giving the robot an abbreviated, “connect the dots” graph-style of
                                         spatial memory.
   337   338   339   340   341   342   343   344   345   346   347