Neural Network and Particle Swarm Optimization Based on Dynamic Obstacle Avoidance and Path Planning for Mobile Robots

Abstract

A method of dynamic obstacle avoidance and path planning based on neural network and particle swarm optimization is proposed. The dynamic environmental information in the workspace for a robot is described by a neural network model. Using this model, the relationship between dynamic obstacle avoidance and the output of the model is established. Then the two-dimensional coding for the planned path is simplified to one-dimensional one. Finally, the particle swarm optimization is introduced to get an optimized collision-free path. The simulation result shows that the proposed method is correct and efficient.