面向制造环境的工业机器人节能轨迹规划
赵俊宇, 张平, 李方, 陈昕叶
华南理工大学计算机科学与工程学院, 广东 广州 510006
Energy Saving Trajectory Planning for Industrial Robot in Manufacturing Environment
ZHAO Junyu, ZHANG Ping, LI Fang, CHEN Xinye
School of Computer Science and Engineering, South China University of Technology, Guangzhou 510006, China
全文:
PDF
(3226 KB)
HTML
( )
输出: BibTeX | EndNote (RIS)
引用本文:
赵俊宇, 张平, 李方, 陈昕叶. 面向制造环境的工业机器人节能轨迹规划[J]. 机器人, 2021, 43(6): 653-663.DOI: 10.13973/j.cnki.robot.200489 .
ZHAO Junyu, ZHANG Ping, LI Fang, CHEN Xinye. Energy Saving Trajectory Planning for Industrial Robot in Manufacturing Environment. ROBOT, 2021, 43(6): 653-663. DOI: 10.13973/j.cnki.robot.200489 .
摘要 在制造环境中,工业机器人节能轨迹规划的实际应用存在2个问题:机器人动力学参数未知;现有节能轨迹规划方法无法保证结果的稳定性.因此,本文提出了面向制造环境的工业机器人节能轨迹规划,包括基于平行BP(backpropagation)神经网络的近似动力学辨识和基于凸优化(CO)的节能轨迹求解法.以UR3机器人为实验平台,近似动力学模型的均方根误差(RMSE)可收敛至2.05×10-3 N.m;且凸优化轨迹规划的求解稳定性优于现有的参数化轨迹规划.实验结果表明:本文提出的节能轨迹规划方案,能应对制造环境中机器人动力学参数未知的情况,同时保证轨迹规划结果的稳定性,因此更适用于制造环境中的工业机器人.
关键词 :
智能制造 ,
工业机器人 ,
节能 ,
轨迹规划 ,
动力学辨识 ,
神经网络 ,
凸优化
Abstract :In the manufacturing environment, there are two problems in the application of energy saving trajectory planning for industrial robot:one is that the robot dynamic parameters are unknown, and the other is that the existing energy saving trajectory planning methods can't guarantee the stability of the results. Therefore, an energy saving trajectory planning for industrial robot in manufacturing environment is proposed, including approximate dynamic identification based on parallel BP (backpropagation) neural networks, and energy saving trajectory solution based on convex optimization (CO). Taking UR3 robot as the experimental platform, the RMSE (root mean squared error) of the approximate dynamic model can converge to 2.05×10-3 N. m, and the solution stability of convex optimization based trajectory planning is better than the existing parametric trajectory planning. The experimental results show that the proposed energy saving trajectory planning scheme can deal with the problem of unknown robot dynamic parameters in the manufacturing environment, while ensuring the stability of the trajectory planning results, so it is more applicable for industrial robots in the manufacturing environment.
Key words :
intelligent manufacturing
industrial robot
energy saving
trajectory planning
dynamic identification
neural network
convex optimization
收稿日期: 2020-11-25
录用日期: 2021-06-24
基金资助: 广东省重点领域研发计划(2019B090915002);国家重点研发计划(2018YFB1700500);中央高校基本科研业务费
通讯作者:
张平,pzhang@scut.edu.cn
E-mail: pzhang@scut.edu.cn
作者简介 : 赵俊宇(1995-),男,硕士.研究领域:智能机器人技术. 张平(1964-),男,博士,教授.研究领域:人工智能,机器人,无人智能系统,人机交互技术. 李方(1981-),女,博士,副教授.研究领域:智能机器人技术,信息物理融合技术,嵌入式技术.
[1] 经济建设司. 关于印发《智能制造发展规划(2016——2020年)》的通知[EB/OL]. (2016-09-28)[2021-02-12]. http://www.mof.gov.cn/gp/xxgkml/jjjss/201612/t20161208_2512227.html. Department of Economic Construction. Notice on printing and distributing Development Plan of Intelligent Manufacturing (2016-2020) [EB/OL].(2016-09-28)[2021-02-12]. http://www.mof.gov.cn/gp/xxgkml/jjjss/201612/t20161208_2512227.html. [2] 国务院. 国务院关于印发《中国制造2025》的通知[EB/OL].(2015-05-08)[2021-02-12].http://www.gov.cn/zhengce/content/2015-05/19/content_9784.htm. The State Council. Notice of the state council concerning the issuance of made in China 2025 [EB/OL]. (2015-05-08)[2021-02-12].http://www.gov.cn/zhengce/content/2015-05/19/content_9784.htm. [3] Gao M D, He K, Li L, et al. Areview on energy consumption, energy efficiency and energy saving of metalforming processes from different hierarchies[J]. Processes, 2019, 7(6). DOI:10.3390/pr7060357. [4] Wu D W, Liu Q, Xu W J, et al. External force detectionfor physical human-robot interaction using dynamic modelidentification[M]//Lecture Notes in Computer Science, Vol.10462. Berlin,Germany:Springer, 2017:581-592. [5] Asl R M, Hagh Y S, Simani S, et al. Adaptive square-rootunscented Kalman filter:An experimental study of hydraulic actuator stateestimation[J]. Mechanical Systems and Signal Processing, 2019, 132:670-691. [6] Brunot M, Janot A, Young P C, et al. An improvedinstrumental variable method for industrial robot model identification[J].Control Engineering Practice, 2018, 74:107-117. [7] Mizuno N, Nguyen C H. Parameters identificationof robot manipulator based on particle swarm optimization[C]//13th IEEEInternational Conference on Control & Automation. Piscataway, USA:IEEE,2017:307-312. [8] Urrea C, Pascal J. Design, simulation,comparison and evaluation of parameter identification methods for anindustrial robot[J]. Computers & Electrical Engineering, 2018, 67:791-806. [9] Agand P, Shoorehdeli M A, Khaki-Sedigh A. Adaptive recurrentneural network with Lyapunov stability learning rules for robot dynamicterms identification[J]. Engineering Applications of ArtificialIntelligence, 2017, 65:1-11. [10] Corke P. Robotics, vision andcontrol:Fundamental algorithms in MATLAB© [M]. Berlin, Germany:Springer, 2017. [11] Hosseini S, Hahn I. Energy-efficient motion planning for electrical drives[C]//IEEE ElectricalPower and Energy Conference. Piscataway, USA:IEEE, 2018:1-7. [12] Hong Y, Kim J, Park FC. Comparative analysis ofenergy-based criteria for dynamics-based robot motion optimization[C]//IEEEConference on Control Technology and Applications. Piscataway, USA:IEEE,2017:175-180. [13] Kaserer D, Gattringer H, MüllerA. Nearly optimal pathfollowing with jerk and torque rate limits using dynamic programming[J].IEEE Transactions on Robotics, 2019, 35(2):521-528. [14] Debrouwere F, van Loock W, Pipeleers G, et al. Time-optimal path followingfor robots with convex-concave constraints using sequential convexprogramming[J]. IEEE Transactions on Robotics, 2013, 29(6):1485-1495. [15] 袁明星. Universal robotUR3e[EB/OL]. (2020-05-29)[2020-11-03].https://www.universal-robots.com/products/ur3-robot/. [19] Universal Robot. Real-timedata exchange (RTDE) guide[EB/OL] . (2020-10-30)[2020-11-03].https://www.universal-robots.com/articles/ur-articles/real-time-data-exchange-rtde-guide/. [20] ROS-industrial. ROS-industrialuniversal robot meta-package[EB/OL]. (2019-11-03)[2020-11-03].https://github.com/ros-industrial/universal_robot.
[1]
张晋, 唐进, 尹建芹. 面向人体动作预测的对称残差网络 [J]. 机器人, 2022, 44(3): 291-298.
[2]
杨天昊, 李云开, 王雅昕, 孟庆浩. 服务机器人的触觉手势识别 [J]. 机器人, 2022, 44(3): 310-320.
[3]
付天宇, 李凤鸣, 崔涛, 宋锐, 王艳红. 基于视觉/力觉的机器人协同缝制系统 [J]. 机器人, 2022, 44(3): 352-360.
[4]
李陇南, 黄攀峰, 马志强. 基于时变输出约束的机器人遥操作有限时间控制方法 [J]. 机器人, 2022, 44(1): 19-34,44.
[5]
余慧瑾, 方勇纯, 韦知辛. 基于多传感融合的自主发育网络场景识别方法 [J]. 机器人, 2021, 43(6): 706-714.
[6]
苗青, 孙晨阳, 张明明, 褚开亚. 基于任务表现的机器人辅助康复自适应控制策略 [J]. 机器人, 2021, 43(5): 539-546,556.
[7]
陈宗海, 裴浩渊, 王纪凯, 戴德云. 基于单目相机的视觉重定位方法综述 [J]. 机器人, 2021, 43(3): 373-384.
[8]
黄沿江, 陈锴彬, 王恺, 杨丽新, 张宪民. 基于人体手臂运动意图反馈的人机顺应协作 [J]. 机器人, 2021, 43(2): 148-155.
[9]
杨超, 张铭钧, 吴珍臻, 张志强, 姚峰. 作业型水下机器人纵、横倾姿态自适应区域控制方法 [J]. 机器人, 2021, 43(2): 224-233.
[10]
安海博, 梁炜, 张吟龙. 机器人RV减速器声发射信号传播机理分析及实验研究 [J]. 机器人, 2020, 42(5): 557-567.
[11]
赵威, 王锴, 徐皑冬, 曾鹏, 杨顺昆, 孙越, 郭海丰. 面向智能制造的工业机器人健康评估方法 [J]. 机器人, 2020, 42(4): 460-468.
[12]
张玉明, 吴青聪, 陈柏, 吴洪涛, 刘焕瑞. 下肢软质康复外骨骼机器人的模糊神经网络阻抗控制 [J]. 机器人, 2020, 42(4): 477-484,493.
[13]
侯澈, 赵忆文, 张弼, 李英立, 赵新刚. 基于最优激励位姿序列的机械臂负载估计 [J]. 机器人, 2020, 42(4): 503-512.
[14]
张阳阳, 黄英, 刘月, 刘彩霞, 刘平, 张玉刚. 基于多传感器信息融合的人类抓握特征学习及物体识别 [J]. 机器人, 2020, 42(3): 267-277.
[15]
陈友东, 胡澜晓. 工业机器人负载动力学参数辨识方法 [J]. 机器人, 2020, 42(3): 325-335.