基于DBSCAN算法的改进 RRT-Connect 路径规划研究  

Research on Improved RRT-Connect Path Planning Based on DBSCAN Algorithm

作　　者：李刘洋 王可庆 焦思韬 周奇 LI Liuyang;WANG Keqing;JIAO Sitao;ZHOU Qi(School of Automation,Nanjing University of Information Science and Technology,Nanjing,Jiangsu 210044,China)

机构地区：[1]南京信息工程大学自动化学院,江苏南京210044

出　　处：《计算技术与自动化》2025年第1期1-6,共6页Computing Technology and Automation

基　　金：江苏高校“青蓝工程”资助项目。

摘　　要：针对双向快速扩展随机树(RRT-Connect)算法收敛速度慢、路径搜索效率低、路径曲折的问题,提出了一种基于DBSCAN算法的改进RRT-Connect算法。在RRT-Connect算法基础上加入节点引力场引导新节点产生方向,使收敛速度变快;同时通过引入椭圆采样方法,缩小采样范围,提高路径规划效率;最后在改进RRT-Connect的基础上引入DBSCAN聚类算法,使得到的规划路径更加平滑可靠,增强算法的鲁棒性。为了验证改进后的算法优化效果,分别在不同环境中与RRT算法、RRT-Connect算法进行仿真比较。仿真实验表明,改进后的RRT-Connect算法路径规划效果均要优于其他两种算法,不仅加快了路径规划速度,而且得到的路径接近最优解,具有普遍适用性、鲁棒性高等特点。Aiming at the problems of slow convergence speed,low path search efficiency and tortuous path of RRT-Connect algorithm,an improved RRT-Connect algorithm based on DBSCAN algorithm is proposed.On the basis of the RRT-Connect algorithm,the node gravitational field is added to guide the direction of the new node,which makes the convergence speed faster.At the same time,by introducing the elliptical sampling method,the sampling range is reduced to improve the efficiency of path planning.Finally,based on the improved RRT-Connect,the DBSCAN clustering algorithm is introduced to make the obtained planning path smoother and more reliable,and enhance the robustness of the algorithm.In order to verify the optimization effect of the improved algorithm,it is simulated and compared with the RRT algorithm and the RRT-Connect algorithm in different environments.The simulation results show that the improved RRT-Connect algorithm has better path planning effect than the other two algorithms.It not only accelerates the path planning speed,but also obtains the path close to the optimal solution,which has the characteristics of universal applicability and high robustness.

关 键 词：RRT-Connect算法 DBSCAN算法 椭圆采样 引力场 路径规划 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]