Neural dynamics for mobile robot adaptive control

Abstract

In this thesis, we investigate how dynamics in recurrent neural networks can be used to solve some specific mobile robot problems. We have designed a motion control approach based on a novel recurrent neural network. The advantage of this approach is that, no knowledge about the dynamic model is required, and no synaptic weight changing is needed in presence of time varying parameters. Furthermore, this approach allows a single fixed-weight network to act as a dynamic controller for several distinct robots. To generate the robot behavior over time, we adopted the theory of neural fields. We designed a framework to navigate a robot to its goal in an unknown environment without any collisions with static or moving obstacles. In addition, we could optimize the target path through intermediate homebases. This framework has also produced a simple and elegant solution for the problem of moving multiple robots in formation. The objective is to acquire a target, avoid obstacles and keep a geometric configuration at the same time.