Situated Learning of a Behavior-Based Mobile Robot Path Planner

In this paper, we propose a behaviorbased path planner that can self learn in anunknown environment. A situated learning algorithm is designed which allows therobot to learn to coordinate several concurrent behaviors and improve its performanceby interacting with the environmellt. Behaviors are implemented using CMAC neuralnetworks. A simulation environment is set up and some simulation experiments arecarried out to rest our learning algorithm.