COLLISION DETECTION FOR MULTIPLE ROBOT MANIPULATORS BY USING ORTHOGONAL NEURAL NETWORKS

This article discusses the application of orthogonal neural networks t o detect collisions between multiple robot manipulators that work in a n overlapped space. By applying an expansion/shrinkage algorithm, the problem of collision detection between arms is transformed into that a mong cylinders (or rectangular solids) and line segments. This mapping simplifies the collision detection problem and thus neural networks c an be applied to solve it. The property of parallel processing enables neural networks to detect collisions rapidly. A single-layer orthogon al neural network is developed to avert the problems of conventional m ultilayer feedforward neural networks such as initial weights and the number of layers and processing elements. This orthogonal neural netwo rk can approximate various functions and is used to calculate forward solution and to detect collisions. An efficient neural network system for collision detection is also developed. (C) 1995 John Wiley & Sons, Inc.