基于RRT的机械臂路径规划改进算法

Improved algorithm for robotic arm path planning based on RRT

针对快速随机树(Rapidly-exploring Random Trees,RRT)算法在复杂环境下规划效率低的问题,提出一种基于RRT的机械臂路径规划改进算法。首先,在初始采样时应用角度约束采样策略限制采样区域,提升采样质量。然后,在扩展节点时融合人工势场法的思想,设定动态步长加快算法的收敛,提升算法在障碍物空间的探索效率,当算法陷入局部极小值时,采用节点拒绝策略快速脱离。最后,将规划路径进行简化处理,并利用B样条曲线平滑拐点提高路径质量。仿真结果表明,改进算法相比传统RRT算法,扩展更具导向性,收敛速度更快,可以有效避免局部极小值。

In order to solve the problem of low planning efficiency of rapidly-exploring random trees(RRT)algorithm in complex environments,an improved algorithm for robotic arm path planning based on RRT was proposed.Firstly,the angle constraint sampling strategy is applied to limit the sampling area during the initial sampling to improve the sampling quality.Then,the idea of artificial potential field method is integrated when expanding nodes,and the dynamic step size is set to accelerate the convergence of the algorithm,so as to improve the exploration efficiency of the algorithm in obstacle space.When the algorithm falls into a local minimum,a node rejection strategy is adopted for quick detachment.Finally,the planned path is simplified,and the B-spline curve is used to smooth the inflection point to improve the path quality.Simulation results show that compared with the traditional RRT algorithm,the improved algorithm has more expansion orientation and faster convergence speed,which can effectively avoid the local minima.