基于APF-RRT^(*)的火龙果采摘机械臂路径规划研究  

Path Planning of Dragon Fruit Harvesting Manipulator Based on APF-RRT

作　　者：商枫楠 罗陈迪 李文涛 梁英凯 肖明玮 陈桥 周学成 Shang Fengnan;Luo Chendi;Li Wentao;Liang Yingkai;Xiao Mingwei;Chen Qiao;Zhou Xuecheng(Guangdong Provincial Key Laboratory of Agricultural Artificial Intelligence(GPKL-AAI),Guangzhou 510642,China;Key Laboratory of Key Technology on Agricultural Machine and Equipment,Ministry of Education,South China Agricultural University,Guangzhou 510642,China;College of Engineering/Guangdong Engineering Research Center for Agricultural Aviation Application(ERCAAA),South China Agricultural University,Guangzhou 510642,China)

机构地区：[1]广东省农业人工智能重点实验室,广州510642 [2]华南农业大学南方农业机械与装备关键技术教育部重点实验室,广州510642 [3]华南农业大学工程学院/广东省农业航空应用工程技术研究中心,广州510642

出　　处：《农机化研究》2025年第6期48-52,71,共6页Journal of Agricultural Mechanization Research

基　　金：广东省科技计划项目(2021年度)(2021B1212040009)。

摘　　要：针对传统RRT算法路径规划过程中存在收敛速度慢、搜索路径不平滑、内存占用多等问题,提出了一种基于APF-RRT*的火龙果采摘机械臂路径规划研究方法。利用RRT*算法重新搜索父节点和布线的原理,针对节点冗余的问题进行改进,减少路径代价;将改进的人工势场法(APF)作为分量偏置扩展点的方向,使随机树偏向目标点生长,避免盲目扩展和提高了路径平滑度。MatLab与CoppeliaSim联合仿真实验表明:APF-RRT^(*)算法相较于传统RRT算法、RRT^(*)算法和APF算法,不仅明显减少了路径点个数和路径长度,缩短了算法时间,提高了路径搜索效率,而且平衡了路径平滑度,适用于在火龙果仿生长环境下采摘机械臂进行避障路径规划。Aiming at overcoming the problems of the disadvantages of traditional RRT algorithm in planning path,including slow convergence speed,poor path smoothness and large memory occupation,a path planning algorithm for dragon fruit harvesting robotic manipulator based on APF-RRT*was proposed.The problem of node redundancy was improved and the cost was reduced,based on the principle of re-searching parent node and routing by RRT^(*)algorithm.The improved artificial potential field method(APF)was used as the direction of the component offset expansion point,so that the random tree grows biased towards the target point,which made blind expansion avoided and the smoothness of the path improved.The joint simulation of Matlab and CoppeliaSim results showed that,compared with the traditional RRT algorithm,RRT^(*)algorithm and APF algorithm,APF-RRT^(*)algorithm not only significantly reduced the number of path points and the length of path,reduced running time and improved the path search efficiency,but also have the quality of the path smoothness.The results demonstrated that the algorithm was suitable for harvesting robotic manipulator in the dragon fruit growth simulation environment to implement obstacle avoidance path planning.

关 键 词：火龙果 采摘机械臂 路径规划 APF-RRT^(*) 改进人工势场 CoppeliaSim 

分 类 号：S225[农业科学—农业机械化工程]