避免路径规划NA算法局部极小值的仿真试验

The Experiment of the Local Minimum Value of the Algorithm for Path Planning

针对已知障碍物形状和位置环境下的机器人全局路径规划问题 ,提出利用神经网络路径规划算法进行路径规划。为解决神经网络路径规划算法的局部极小值问题 ,提出针对障碍物的形状设定各条边的模拟退火初始温度。采用此方法仿真试验的结果表明 ,该方法能够避免某些局部极小值情况 。

In this paper,the problem of path planning is studied for a moving robot in an environment field with obstacles which have shapes and positions known,and the collision free paths are found by using the algorithm based on neural network.To avoid local minimum value,different initial simulated anneal temperatures of each side of obstacles are set.The simulation results show that the computation is simple,the local minimum problem can be avoided,and the constructed path is optimal.