一种基于神经网络的机器人路径规划算法

An Algorithm of Path Planning for Car-like Robots Based on Neural Network

研究已知障碍物形状和位置环境下的全局路径规划问题。给出了一个路径规划算法 ,其能量函数的定义利用神经网络结构 ,根据路径点位于障碍物内外的不同位置选取不同的动态运动方程。规划出的路径达到了折线形的最短无碰路径。仿真研究表明 ,本文提出的算法计算简单 ,收敛速度快 。

In this paper, the problem of global path planning is studied for a moving robot in an environment filled with obstacles whose shapes and positions are known. An planning algorithm is presented based on Energy Function defined using a neural network. It is shown by the simulations that the computation is simple, the convergence of the algorithm is fast, and the constructed path is optimal and piecewise linear.