作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• 人工智能及识别技术 • 上一篇    下一篇

基于动态离散势场的迷宫机器人路径规划

赵 坤,嵇启春,李玲燕   

  1. (西安建筑科技大学信息与控制工程学院,西安 710055)
  • 收稿日期:2012-11-02 出版日期:2013-12-15 发布日期:2013-12-13
  • 作者简介:赵 坤(1988-),女,硕士研究生,主研方向:路径规划算法;嵇启春,教授;李玲燕,硕士研究生

Path Planning for Maze Robot Based on Dynamic Discrete Potential Field

ZHAO Kun, JI Qi-chun, LI Ling-yan   

  1. (School of Information and Control Engineering, Xi’an University of Architecture and Technology, Xi’an 710055, China)
  • Received:2012-11-02 Online:2013-12-15 Published:2013-12-13

摘要: 针对未知环境下的机器人迷宫求解问题,提出一种动态离散势场路径规划算法。为提高路径优化性能,采用引入边界节点的栅格法建立模型,在各栅格的边界节点处定义障碍物状态和势场的数值大小,通过计算可连通相邻节点的累计代价值完成势场的构造。为提高寻优速度,随着环境信息的更新动态改变势场分布,沿势场下降最快方向获得实时重规划路径,引导机器人向目标运动,通过预规划路径的访问状态判断路径是否收敛,避免无用栅格的扩展。仿真实验结果表明,应用该算法可使机器人在复杂未知的迷宫环境中快速、高效地规划出一条折线少、转折角度小的优化路径。

关键词: 未知环境, 路径规划, 动态离散势场, 迷宫求解, 边界节点

Abstract: Aiming at robot solving maze problem in the unknown environment, a path planning algorithm based on dynamic discretely potential is proposed. In order to improve the performance of path optimization, the algorithm uses grids method which including boundary node to model, and by accumulating the values of connected nodes which mean the grid’s status of obstacles to build potential field. Furthermore, to increase search rate, the algorithm dynamically changes potential field as the environment information updated, and obtains the direction which potential values fall to guide the robot moving toward target. The convergence of path is judged by its visit status to avoid extension of useless grids. Simulation experimtental results show that the robot can find out smoothing optimal path quickly and efficiently by using the algorithm in the complex and unknown maze environment.

Key words: unknown environment, path planning, dynamic discrete potential field, maze solving, boundary node

中图分类号: