An Unsupervised Neural Network for Real-Time Low-Level Control of a Mobile Robot: Noise Resistance, Stability, and Hardware Implementation

Abstract

We have recently introduced a neural network mobile robot controller (NETMORC). The controller is based on earlier neural network models of biological sensory-motor control. We have shown that NETMORC is able to guide a differential drive mobile robot to an arbitrary stationary or moving target while compensating for noise and other forms of disturbance, such as wheel slippage or changes in the robot's plant. Furthermore, NETMORC is able to adapt in response to long-term changes in the robot's plant, such as a change in the radius of the wheels. In this article we first review the NETMORC architecture, and then we prove that NETMORC is asymptotically stable. After presenting a series of simulations results showing robustness to disturbances, we compare NETMORC performance on a trajectory-following task with the performance of an alternative controller. Finally, we describe preliminary results on the hardware implementation of NETMORC with the mobile robot ROBUTER.