摘要
针对快速探索随机树算法在局部极小区域做大量失败探索的问题,提出一种自适应加权快速探索随机树算法。分析影响快速探索随机树生长的关键因素,提出在树探索的动态过程中应充分利用探索过程的反馈信息,为树节点赋予自适应权重。根据树节点的自适应权重大小,选择树的生长点。仿真结果表明,该方法能有效地提高树探索效率,缩短规划路径长度。
Rapidly-exploring Random Tree(RRT) algorithm is a practical and promising solution to motion planning problem.The algorithm easily falls into local minima which leads to massive failure exploring.To overcome the shortcoming,key factors affecting the exploring of the tree are analyzed and an adaptive weight method is proposed.Nodes are weighted according to the heuristic information collected from the dynamic exploring process,tree extension is guided by the weight.Simulation results show that the method can improve the quality of the tree and shorten the length of planning path.
出处
《计算机工程》
CAS
CSCD
北大核心
2010年第23期16-18,共3页
Computer Engineering
基金
国家自然科学基金资助项目(60873078)
中央高校基本科研业务费专项基金资助项目(2009ZM0297)
广东省科技计划基金资助项目(2009A040300008)
关键词
运动规划
随机采样
快速探索随机树
自适应权重
motion plan
randomized sampling
Rapidly-exploring Random Tree(RRT)
adaptive weight