A neural networks based collision detection engine for multi-arm robotic systems

Abstract

Modular neural networks are proposed for collision detection among multiple robotic arms sharing a common workspace. The structure of the neural networks is a hybrid between Guassian radial basis function (RBF) neural networks and multilayer perceptron backpropagation (BP) neural networks. This network is used to generate potential fields in the configuration space of the robotic arms. A path planning algorithm based on heuristics is presented. It is shown that this algorithm works better than the conventional potential field methods which carry out the planning in the operational space of the robots. Simulation results are presented for two planar manipulator sharing a common workspace. The algorithm is then extended to the case of two 3-DOF arms moving in 3-D space.