基于改进RRT算法的RoboCup机器人动态路径规划

Dynamic Path Planning Based on an Improved RRT Algorithm for RoboCup Robot

  • 摘要: 针对足球机器人在场上采用反应式方法避障时存在的速度慢、效果差的问题,采用改进的快速扩展随机树(RRT)算法设计了一种能够适应机器人足球赛场动态移动障碍环境的路径规划器.首先,引入基本的快速扩展随机树算法,针对其随机性强、路径过长的缺点,提出了以一定概率选择目标点、增加引力分量以及路径平滑处理等改进方式;引入路径缓存区以及动态扩展随机树的方法来解决移动障碍物环境中的路径规划问题.复杂障碍物环境中的仿真实验表明,改进的规划路径长度比基本快速扩展随机树算法所得路径缩短约20%.最终将策略移植到实体NAO机器人上参加RoboCup比赛,取得世界八强的成绩.

     

    Abstract: To solve the problem of slow speed and low efficiency of the soccer robots using reactive obstacle avoidance strategy at soccer game, an improved rapidly-exploring random tree (RRT) algorithm is adopted, and a path planner based on this algorithm is designed to adapt to the dynamic moving obstacles environment in the robot soccer field. Firstly, the basic RRT algorithm is introduced, and some improvement ways to solve the disadvantages of strong randomness and long path length are proposed, such as probabilistically selecting the target node, adding the gravity component, and smoothing the path. The path planning in dynamic moving obstacles environment is solved by using the methods of path buffer and dynamic-expanding random tree. The simulation in complex obstacle environment shows that the path generated by the improved algorithm is about 20% shorter than the path generated by the basic RRT algorithm. Finally, the strategy is applied to the physical NAO robot to participate in the RoboCup competition and the top eight grade is achieved.

     

/

返回文章
返回