摘要
针对水果采摘的现存问题,对水果采摘机械臂进行合理的运动规划,以达到解放人力、提高采摘效率、降低采收成本的目的。分析水果采摘机器人的国内外研究进展,并就其机械臂采摘过程的关键算法进行比较,最后针对机械臂轨迹规划平滑性差、效率低提出采用B样条曲线和生物智能的算法;针对搜索效率低和局部最小值的问题提出采用基于图搜索的改进算法、改进人工势场法和深度强化学习算法等对策,并在新的运动规划算法、机械臂硬件以及底层控制和多机械臂协作控制等方面进行展望。
Aiming to solve the existing problems of fruit picking,proper movement planning of fruit picking mechanical arm is carried out to improve the efficiency of fruit picking,liberate manpower,and reduce the harvest cost.This paper analyzes the research status of fruit-picking robots at home and abroad and compares the key algorithms of the picking process of the robot arm.Finally,aiming to solve the poor smoothness and low efficiency of the trajectory planning of the robot arm,the algorithm using the B-spline curve and biological intelligence is proposed.In order to solve the problems of low search efficiency and local minimum,the improved algorithm based on graph search,the improved artificial potential field method,and the deep reinforcement learning algorithm are proposed,and the new motion planning algorithm,manipulator hardware,low-level control,and multi-manipulator cooperative control are prospected.
作者
段洁利
王昭锐
叶磊
杨洲
Jieli Duan;Zhaorui Wang;Lei Ye;Zhou Yang(College of Engineering,South China Agricultural University,Guangzhou,510600,China;Guangdong Laboratory for Lingnan Modern Agriculture Science and Technology,Guangzhou,510600,China;Laboratory of Conservation and Precision Utilization of Characteristic Agricultural Resources in Mountainous Areas,Jiaying University,Meizhou,514000,China)
出处
《智能化农业装备学报（中英文）》
2021年第2期7-17,共11页
Journal of Intelligent Agricultural Mechanization
基金
国家重点研发计划项目(2020YFD1000104)
岭南现代农业实验室科研项目(NT2021009)
财政部和农业农村部:现代农业产业技术体系建设专项资金(CARS-31-10)。
关键词
水果采摘
智能化
非结构性环境
机械臂
运动规划
fruit picking
intelligent
unstructured environment
robot arm
motion planning
