基于G-RRT*算法的煤矸石分拣机器人路径规划

朱子祺; 李创业; 代伟

doi:10.13272/j.issn.1671-251x.2021090015

基于G-RRT*算法的煤矸石分拣机器人路径规划

doi: 10.13272/j.issn.1671-251x.2021090015

1.
国家能源集团神东煤炭集团公司洗选中心, 陕西榆林　719300
2.
郑州机电工程研究所, 河南郑州　450015
3.
中国矿业大学信息与控制工程学院, 江苏徐州　221116

基金项目: 国家自然科学基金面上项目（61973306）。

详细信息

作者简介:
朱子祺（1982-），男，江苏徐州人，高级工程师，研究方向为煤炭加工及高质化、煤矿智能化，E-mail：Studyzhu@163.com

中图分类号: TD67
计量
- 文章访问数: 1249
- HTML全文浏览量: 66
- PDF下载量: 42
- 被引次数: 0
出版历程
- 收稿日期: 2021-09-05
- 修回日期: 2022-03-07
- 网络出版日期: 2022-03-22

Path planning of coal gangue sorting robot based on G-RRT* algorithm

1.
Washing Center, CHN Energy Shendong Coal Group Co., Ltd., Yulin 719300, China
2.
Zhengzhou Institute of Electric and Mechanical Engineering, Zhengzhou 450015, China
3.
School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116, China

摘要

摘要: 由于煤矸石分拣环境复杂，为了避免机器人与障碍物发生碰撞，提高分拣效率，对机器人进行路径规划十分必要。分析了煤矸石分拣系统原理，将煤矸石分拣机器人路径规划问题归结为在障碍物环境下规划出一条从给定起点到目标点的无碰撞路径，且需同时满足速度快、避免与障碍物碰撞2个约束条件。结合笛卡尔空间和关节空间的优点，提出一种在关节空间进行路径规划、在笛卡尔空间进行碰撞检测的煤矸石分拣机器人路径规划方案，该方案不需要对机器人进行运动学求逆，且可避免在关节空间中描述障碍物。针对RRT*路径规划算法存在盲目性的问题，提出一种变概率的目标偏置策略，并将其引入RRT*算法，得到G-RRT*算法。变概率的目标偏置策略在无障碍物区域增大目标偏置概率值，以增强算法的目标导向性；而在障碍物区域减小目标偏置概率值，以保证算法的避障能力。G-RRT*算法将变概率的目标偏置策略与RRT*算法相结合，既保留了RRT*算法路径长度渐进最优的特点，也提高了算法的目标导向性，可极大地提高路径规划效率。实验结果表明，与加入固定概率目标偏置策略的RRT-Connect算法和RRT算法相比，采用G-RRT*算法得到的路径长度平均值最小，说明G-RRT*算法更适用于煤矸石分拣机器人路径规划。
- 煤矸石分拣 /
- 机器人 /
- 路径规划 /
- 快速扩展随机树 /
- 变概率的目标偏置策略 /
- G-RRT*算法
Abstract: The coal gangue sorting environment is complex. In order to avoid the collision between robot and obstacles and improve sorting efficiency, it is necessary to carry out path planning for robot. The principle of coal gangue sorting system is analyzed. The path planning problem of coal gangue sorting robot is summed up as planning a collision-free path from a given starting point to a target point in the environment of obstacles, and the two constraints of high speed and avoiding collision with obstacles must be met at the same time. Combining the advantages of Cartesian space and joint space, a path planning scheme for coal gangue sorting robot with path planning in joint space and collision detection in Cartesian space is proposed. The scheme does not need to carry out kinematic inversion of the robot, and can avoid describing obstacles in joint space. In order to solve the problem of blindness in the improved rapidly-exploring random trees (RRT*) path planning algorithm, a variable probability target bias strategy is proposed and introduced into RRT* algorithm to obtain the G-RRT* algorithm. The target bias strategy with variable probability increases the target bias probability in the obstacle-free area so as to enhance the target orientation of the algorithm. In the obstacle area, the target bias probability value is reduced to ensure the obstacle avoidance capability of the algorithm. The G-RRT* algorithm combines the variable probability target bias strategy with RRT* algorithm. The G-RRT* algorithm not only retains the asymptotic optimal path length characteristic of RRT* algorithm, but also improves the target orientation of the algorithm, and can improve the path planning efficiency greatly. The experimental results show that compared with RRT-Connect algorithm and RRT algorithm with fixed probability target bias strategy, the G-RRT* algorithm can get the shortest average path length, and is more suitable for path planning of coal gangue sorting robot.
- coal gangue sorting /
- robot /
- path planning /
- rapidly-exploring random trees /
- variable probability target bias strategy /
- G-RRT* algorithm

HTML全文

图 1 煤矸石分拣系统

Figure 1. Coal gangue sorting system

下载: 全尺寸图片幻灯片

图 2 机器人路径规划方案

Figure 2. Robot path planning scheme

下载: 全尺寸图片幻灯片

图 3 机器人机械结构

Figure 3. Robot mechanical structure

下载: 全尺寸图片幻灯片

图 4 机器人连杆和障碍物简化模型

Figure 4. Simplified model of robot link and obstacle

下载: 全尺寸图片幻灯片

图 5 RRT算法节点扩展

Figure 5. Node extension of RRT algorithm

下载: 全尺寸图片幻灯片

图 6 RRT*算法节点扩展

Figure 6. Node extension of RRT* algorithm

下载: 全尺寸图片幻灯片

图 7 目标偏置策略效果对比

Figure 7. Comparison of target bias strategy effects

下载: 全尺寸图片幻灯片

图 8 引入固定概率目标偏置的RRT算法实验结果

Figure 8. Experimental results of RRT algorithm introducing fixed probability target bias

下载: 全尺寸图片幻灯片

图 9 引入固定概率目标偏置的RRT-Connect算法实验结果

Figure 9. Experimental results of RRT-Connect algorithm introducing fixed probability target bias

下载: 全尺寸图片幻灯片

图 10 G-RRT*算法实验结果

Figure 10. Experimental results of G-RRT* algorithm

下载: 全尺寸图片幻灯片

图 11 3种算法实验结果对比

Figure 11. Comparison of experimental results of three algorithms

下载: 全尺寸图片幻灯片

表 1 算法性能参数对比

Table 1. Comparison of algorithm performance parameters

算法平均时间/s 路径长度
平均值/rad

RRT 5.66 7.57
RRT-Connect 2.98 11.86
G-RRT* 4.34 6.79

下载: 导出CSV

参考文献(21)

[1]	董书宁,刘再斌,程建远,等. 煤炭智能开采地质保障技术及展望[J]. 煤田地质与勘探,2021,49(1):21-31. doi: 10.3969/j.issn.1001-1986.2021.01.003 DONG Shuning,LIU Zaibin,CHENG Jianyuan,et al. Technologies and prospect of geological guarantee for intelligent coal mining[J]. Coal Geology & Exploration,2021,49(1):21-31. doi: 10.3969/j.issn.1001-1986.2021.01.003
[2]	徐亮. 我国煤炭开发建设现状与“十四五”展望[J]. 中国煤炭,2021,47(3):44-48. doi: 10.3969/j.issn.1006-530X.2021.03.006 XU Liang. The present situation and expectation of coal exploitation and construction in China[J]. China Coal,2021,47(3):44-48. doi: 10.3969/j.issn.1006-530X.2021.03.006
[3]	张维宸. 能源安全视角下煤炭大国开采政策对比[J]. 国土资源情报,2021(3):16-27. doi: 10.3969/j.issn.1674-3709.2021.03.003 ZHANG Weichen. Comparison of mining policies in coal countries from the perspective of energy security[J]. Land and Resources Information,2021(3):16-27. doi: 10.3969/j.issn.1674-3709.2021.03.003
[4]	张永超,于智伟,丁丽林. 基于强化学习的煤矸石分拣机械臂智能控制算法研究[J]. 工矿自动化,2021,47(1):36-42. ZHANG Yongchao,YU Zhiwei,DING Lilin. Research on intelligent control algorithm of coal gangue sorting robot arm based on reinforcement learning[J]. Industry and Mine Automation,2021,47(1):36-42.
[5]	蒋卫祥. 增量式矿石自动化分拣系统研究[J]. 矿业研究与开发,2020,40(11):150-155. JIANG Weixiang. Study on the incremental automatic ore sorting system[J]. Mining Research and Development,2020,40(11):150-155.
[6]	夏晶,张昊,周世宁,等. 煤矸分拣机器人动态拣取避障路径规划[J]. 煤炭学报,2021,46(增刊1):570-577. XIA Jing,ZHANG Hao,ZHOU Shining,et al. Dynamic picking and obstacle avoidance path planning of coal gangue sorting robot[J]. Journal of China Coal Society,2021,46(S1):570-577.
[7]	曹现刚,李宁,王鹏,等. 基于比例导引法的机械臂拣矸过程轨迹规划方法研究[J]. 煤炭工程,2019,51(5):154-158. CAO Xiangang,LI Ning,WANG Peng,et al. Research and simulation on priority and path planning of manipulator gangue picking[J]. Coal Engineering,2019,51(5):154-158.
[8]	曾俊宝,李硕,李一平,等. 便携式自主水下机器人控制系统研究与应用[J]. 机器人,2016,38(1):91-97. ZENG Junbao,LI Shuo,LI Yiping,et al. Research and application of the control system for a portable autonomous underwater vehicle[J]. Robot,2016,38(1):91-97.
[9]	薛光辉,候称心,张云飞,等. 煤矿巷道修复重载作业机器人现状与发展趋势[J]. 工矿自动化,2020,46(9):8-14. XUE Guanghui,HOU Chenxin,ZHANG Yunfei,et al. Current situation and development trend of heavy-duty operation robot for coal mine roadway repair[J]. Industry and Mine Automation,2020,46(9):8-14.
[10]	于乾坤,王国磊,任田雨,等. 一种移动喷涂机器人的高效站位优化方法[J]. 机器人,2017,39(2):249-256. YU Qiankun,WANG Guolei,REN Tianyu,et al. An efficient base position optimization method for mobile painting robot[J]. Robot,2017,39(2):249-256.
[11]	曹现刚,吴旭东,王鹏,等. 面向煤矸分拣机器人的多机械臂协同策略[J]. 煤炭学报,2019,44(增刊2):763-774. CAO Xiangang,WU Xudong,WANG Peng,et al. Collaborative strategy of multi-manipulator for coal-gangue sorting robot[J]. Journal of China Coal Society,2019,44(S2):763-774.
[12]	赵明辉,宣鹏程,张少宾. 并联煤矸石分拣机器人的结构设计及分析[J]. 机床与液压,2021,49(5):55-59. doi: 10.3969/j.issn.1001-3881.2021.05.011 ZHAO Minghui,XUAN Pengcheng,ZHANG Shaobin. Structure design and analysis for parallel gangue sorting robot[J]. Machine Tool & Hydraulics,2021,49(5):55-59. doi: 10.3969/j.issn.1001-3881.2021.05.011
[13]	王鹏,曹现刚,马宏伟,等. 基于余弦定理−PID的煤矸石分拣机器人动态目标稳准抓取算法[J]. 煤炭学报,2020,45(12):4240-4247. WANG Peng,CAO Xiangang,MA Hongwei,et al. Dynamic target steady and accurate grasping algorithm of gangue sorting robot based on cosine theorem-PID[J]. Journal of China Coal Society,2020,45(12):4240-4247.
[14]	张永超,于智伟,丁丽林. 基于机器视觉的煤矸石检测研究[J]. 煤矿机械,2021,42(4):32-34. ZHANG Yongchao,YU Zhiwei,DING Lilin. Research on coal gangue detection based on machine vision[J]. Coal Mine Machinery,2021,42(4):32-34.
[15]	YU Xue,CHEN Weineng,GU Tianlong,et al. ACO-A:Ant colony optimization plus A for 3-D traveling in environments with dense obstacles[J]. IEEE Transactions on Evolutionary Computation,2019,23(4):617-631. doi: 10.1109/TEVC.2018.2878221
[16]	LE A T, BUI M Q, LE T D, et al. D* Lite with Reset: Improved version of D* Lite for complex environment[C]//First IEEE International Conference on Robotic Computing, Taichung, 2017.
[17]	NAZARAHARI M,KHANMIRZA E,DOOSTIE S. Multi-objective multi-robot path planning in continuous environment using an enhanced genetic algorithm[J]. Expert Systems with Applications,2019,115:106-120. doi: 10.1016/j.eswa.2018.08.008
[18]	SUN Ping,SHAN Rui. Predictive control with velocity observer for cushion robot based on PSO for path planning[J]. Journal of Systems Science and Complexity,2020,33(4):988-1011. doi: 10.1007/s11424-020-8375-x
[19]	KARAMAN S,FRAZZOLI E. Sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research,2011,30(7):846-894. doi: 10.1177/0278364911406761
[20]	CAO Xiaoman,ZOU Xiangjun,JIA Chunyang,et al. RRT-based path planning for an intelligent litchi-picking manipulator[J]. Computers and Electronics in Agriculture,2019,156:105-118. doi: 10.1016/j.compag.2018.10.031
[21]	张云峰,马振书,孙华刚,等. 基于改进快速扩展随机树的机械臂路径规划[J]. 火力与指挥控制,2016,41(5):25-30. doi: 10.3969/j.issn.1002-0640.2016.05.006 ZHANG Yunfeng,MA Zhenshu,SUN Huagang,et al. Path planning of manipulators based on improved rapidly-exploring random tree[J]. Fire Control & Command Control,2016,41(5):25-30. doi: 10.3969/j.issn.1002-0640.2016.05.006