3D path planning for mobile robots using annealing neural network

Abstract

This paper presents a novel potential field based 3D path planning technique for differential drive mobile robots, moving in known environment. The path planners are based on description of the obstacles by simulated annealing neural networks. The generated paths are piecewise linear with changing directions at the corners of the obstacles. The proposed planner can be successfully applied to snake robots, flying robots, and control of Gantry cranes. Several simulation results show the effectiveness of the proposed algorithm.