Trajectory Planning Method for Apple Picking Manipulator Based on Stepwise Migration Strategy

被引：0
|
作者：
Zheng C. [1 ]
Gao P. [1 ]
Gan H. [2 ]
Tian Y. [1 ]
Zhao Y. [1 ]
机构：
[1] School of Technology, Beijing Forestry University, Beijing
[2] Department of Biosystems Engineering and Soil Science, University of Tennessee, Knoxville, 37996, TN
来源：
Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery | 2020年 / 51卷 / 12期
关键词：
Apple; Deep deterministic policy gradient algorithm; Migration learning; Picking manipulator; Trajectory planning;
D O I：
10.6041/j.issn.1000-1298.2020.12.002
中图分类号：
学科分类号：
摘要：
Picking trajectory planning is one of the important research aspects of apple picking manipulator. The unstructured natural environment leads to low training efficiency for picking trajectory planning based on deep reinforcement learning. A deep deterministic policy gradient algorithm (DDPG) based on a stepwise migration strategy was proposed for apple picking trajectory planning. Firstly, a progressive spatially constrained stepwise training strategy based on DDPG was put forward to solve the problem of hard converging in natural environments. Secondly, the transfer learning idea was utilized to migrate the strategies obtained from the obstacle-free scenario to the simple obstacle scenario, from the simple obstacle scenario to the hybrid obstacle scenario, to accelerate the training process in an obstacle scenario from prior strategies and guide the obstacle avoidance trajectory planning of the apple picking manipulator. Finally, the simulation experiments on the multi-degree-of-freedom apple picking manipulator for picking trajectory planning were carried out, and the results showed that the stepwise migration strategy can improve the training efficiency and network performance of the DDPG algorithm. It was validated that the trajectory planning method for apple picking manipulator based on stepwise migration strategy was feasible. © 2020, Chinese Society of Agricultural Machinery. All right reserved.
引用
收藏
页码：15 / 23
页数：8
相关论文
共 25 条
  • [1] LIU Xiaoyang, ZHAO Dean, JIA Weikuan, Et al., Fruits segmentation method based on super pixel features for apple harvesting robot, Transactions of the Chinese Society for Agricultural Machinery, 50, 11, pp. 15-23, (2019)
  • [2] LIU Jizhan, ZHU Xinxin, YUAN Yan, Depth-sphere transversal method for on-branch citrus fruit recognition, Transactions of the Chinese Society for Agricultural Machinery, 48, 10, pp. 32-39, (2017)
  • [3] TIEN T N, ERDAL K, JOSSE D B, Et al., Task and motion planning for apple harvesting robot, IFAC Proceedings Volumes, 46, 18, pp. 247-252, (2013)
  • [4] YIN Jianjun, DONG Wenlong, LIANG Lihua, Et al., Optimization method of agricultural robot path planning in complex environment, Transactions of the Chinese Society for Agricultural Machinery, 50, 5, pp. 17-22, (2019)
  • [5] JIA Qingxuan, CHEN Gang, SUN Hanxu, Et al., Path planning for space manipulator to avoid obstacle based on A<sup>*</sup> algorithm, Journal of Mechanical Engineering, 46, 13, pp. 109-115, (2010)
  • [6] LIU Ke, LI Ke, SU Lei, Et al., Robot 3D path planning method based on ant colony algorithm and parameter transfer, Transactions of the Chinese Society for Agricultural Machinery, 51, 1, pp. 29-36, (2020)
  • [7] YUAN Yanwei, ZHANG Xiaochao, HU Xiao'an, Algorithm for optimization of apple harvesting path and simulation, Transactions of the CSAE, 25, 4, pp. 141-144, (2009)
  • [8] ZHANG Qiang, CHEN Bingkui, LIU Xiaoyong, Et al., Ant colony optimization with improved potential field heuristic for robot path planning, Transactions of the Chinese Society for Agricultural Machinery, 50, 5, pp. 23-32, (2019)
  • [9] WANG Yu, CHEN Haitao, LI Haichuan, 3D path planning approach based on gravitational search algorithm for sprayer UAV, Transactions of the Chinese Society for Agricultural Machinery, 49, 2, pp. 28-33, (2018)
  • [10] YUAN Chaochun, WENG Shuofeng, HE Youguo, Et al., Integration algorithm of path planning and decision-making based on improved artificial potential field, Transactions of the Chinese Society for Agricultural Machinery, 50, 9, pp. 394-403, (2019)
123