Waypoint-based Mobile Robot Navigation

Abstract

A novel robot navigation method is presented that acquires waypoints during reactive exploration for use by a deliberative system in planning future movements through the same environment. A range of methods could be used for either the reactive or deliberative navigation, but, in the current work, an incremental decision tree method is used to navigate the robot reactively from the specified initial position to its destination and a genetic algorithm method is used to perform the deliberative navigation. In contrast with many deliberative approaches, the new method does not require complete prior knowledge of the environment, it is not necessary to make assumptions regarding the geometry of obstacles and it is always possible to revert to reactive navigation in unknown or changing environments or when time constraints are particularly demanding.