Explosive Ordnance Disposal Robot Path Planning Based on Danger Model Immune Wavelet Neural Network

Abstract

Explosive ordnance disposal robot path planning is a nondeterministic polynomial time (NP) problem, traditional optimization methods are not very effective to it, which are easy to plunge into local minimum. In this paper, a new algorithm-Danger Model Immune Wavelet Neural Network (DIWNN) is improved. It is proposed to initialize the weights and biases of wavelet neural network (WNN), the ergodic weights and biases are used for further net-training. The path planning for explosive ordnance disposal robot is conducted by using the well-trained wavelet network. The simulation results show that the algorithm is valid, and indicate the advantage of this algorithm in optimization, and improve path planning capability.