Robot path planning using resistive grids

Abstract

The use of resistive grids for parallel analogue computation was first suggested by Horn, and has more recently been exploited successfully by Carver Mead and his co-workers at Caltech, for example for building silicon models of the retina. These resistive networks cannot strictly be described as 'neural networks' in the conventional sense, but they do perform local, parallel, analogue computation. Moreover, any hardware implementation will have similar benefits in terms of fault-tolerance and speed of operation as an implementation of more standard neural network algorithms. The authors have extended the range of applications of resistive grids to include the task of robot path planning. The overall aim of the project is to develop an autonomous mobile robot capable of real-time navigation in a 2-D environment. The paper describes the work which has been performed on the path-planning component of the project.