NEURAL FIELDS FOR BEHAVIOR-BASED CONTROL OF MOBILE ROBOTS

We present a navigation system using the concept of neural fields and apply it to generate a mobile robots behavior over time. Neural fields are biologically inspired, and equivalent to continuous recurrent neural networks. Here, we used them to navigate the mobile robot to its goal in an unknown environment without any collisions with static or moving obstacles. Furthermore, their competitive dynamics will be used to optimize the target path through intermediate home-bases. Several simulation results are presented that show the effectiveness of the approach.