• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊

计算机工程与科学

• 人工智能与数据挖掘 • 上一篇    下一篇

基于启发式Bi-RRT算法的虚拟手臂运动规划

陈静杰,耿丽琴   

  1. (中国民航大学电子信息与自动化学院,天津 300300)
  • 收稿日期:2018-03-12 修回日期:2018-06-20 出版日期:2019-03-25 发布日期:2019-03-25
  • 基金资助:

    国家自然科学基金(60832011);天津市科技攻关计划重点项目(06YFGZGX00700)

Virtual arm motion planning based on
heuristic Bi-RRT algorithm

CHEN Jingjie,GENG Liqin   

  1. (College of Electronic Information and Automation,Civil Aviation University of China,Tianjin 300300,China)
     
  • Received:2018-03-12 Revised:2018-06-20 Online:2019-03-25 Published:2019-03-25

摘要:

为提高虚拟人手臂在复杂多障碍物空间进行维修时的运动路径规划效率,提出一种基于启发式BiRRT的路径规划算法。在运用Bi-RRT算法的基础上,结合启发式搜索思想对腕关节进行路径规划,通过比较多个随机搜索点与目标点的距离,保留距离目标点最近的随机搜索点,使随机树有方向地进行扩展,减少无效的搜索。仿真实验结果表明,启发式Bi-RRT算法较传统的RRT算法和BiRRT算法有更好的搜索效果,搜索效率更高,对于7自由度虚拟手臂的运动路径规划也有较好的效果。
 

关键词: 虚拟人手臂, 运动路径规划, 快速搜索随机树, 启发式

Abstract:

In order to improve the efficiency of the motion path planning of virtual human arms when it is repairing in complex multi-obstacle space, we propose a path planning method based on the heuristic Bi-RRT algorithm. Combining with the heuristic searching idea based on the Bi-RRT algorithm, we make a  path planning of the wrist joint. Multiple  distances between the random search point and the target point are compared, and the random search points with the shortest distance to the target point are remained. This makes the random tree have a certain direction of expansion and invalid search is reduced. Simulation results show that the heuristic Bi-RRT algorithm has better search results and a higher search efficiency than the traditional RRT algorithm and Bi-RRT algorithm. It also has a good effect on the motion path planning of 7-DOF virtual arms.
 

Key words: virtual human arm, motion path planning, rapidly-exploring random tree, heuristic