期刊文献+

基于增强学习的机械臂轨迹跟踪控制 被引量:19

Robotic trajectory tracking control method based on reinforcement learning
下载PDF
导出
摘要 为了提高机器臂轨迹跟踪控制器的工作性能,提出基于增强学习的机械臂轨迹跟踪控制方法。介绍了增强学习的基本原理,提出基于SARSA算法的增强学习补偿控制策略。利用比例—微分(PD)控制器完成了基本的稳定任务后,再利用增强学习算法实现了对未知干扰因素的补偿,提升了对不同未知情况的适应能力。实验结果验证了自适应离散化增强学习方法在机械臂轨迹跟踪问题中的可行性和有效性,明显提高了控制器的学习速度。 To improve the working performance of robotic trajectory tracking controller,the robotic trajectory tracking control method based on reinforcement learning was proposed.The basic principle of reinforcement learning was introduced,and then the robot trajectory tracking control strategy based on SARSA was proposed.By using the reinforcement learning,the unknown disturbance factors were compensated and the adaptability to the unknown was improved after the PD control method was applied.The experimental results verified the feasibility and effectiveness of the reinforcement learning method in the trajectory tracking problem of robot arms,and the learning speed of the controller was enhanced.
作者 刘卫朋 邢关生 陈海永 孙鹤旭 LIU Weipeng;XING Guansheng;CHEN Haiyong;SUN Hexu(School of Control Science and Engineering,Hebei University of Technology,Tianjin 300130,China;School of Automation and Electronic Engineering,Qingdao University of Science and Technology,Qingdao 266042,China)
出处 《计算机集成制造系统》 EI CSCD 北大核心 2018年第8期1996-2004,共9页 Computer Integrated Manufacturing Systems
基金 河北省科技计划资助项目(17211804D) 天津市教委科研计划资助项目(20140728) 河北省自然科学基金资助项目(F2018202078) 河北省首批青年拔尖人才支持计划资助项目(210003) 天津市自然科学基金资助项目(16JCQNJC04200)~~
关键词 机器人 增强学习 轨迹跟踪 比例-微分控制器 前馈神经网络 robot reinforcement learning trajectory tracking PD controller feedforward neural network
  • 相关文献

参考文献2

二级参考文献24

  • 1Dixon W E, Zerqeroqlu E, Dawson D M. Global robust output feedback tracking control of robot manipulators[J]. Robotica, 2004, 22(4): 351-357.
  • 2Reyesa F, Kelly R. Experimental evaluation of model,based controllers on a direct drive robot arm[J]. Mechatronics, 2001, 11(3): 267-282.
  • 3Wai R J, Chen P C. Robust neural- fuzzy-network control for robot manipulator including actuator dynamics[J]. IEEE Transactions on Industry Electronics, 2006, 53(4): 1328-1349.
  • 4Ren Xuemei, Rad A B, Lewis F L. Neural network-based compensation control of robot manipulators with unknown dynamics[C]. The American Control Conference, New York, USA, 2007.
  • 5Lewis F L, Yesildirek A, Liu K. Multilayer neural-net robot controller with guaranteed tracking performance[J]. IEEE Transactions on Neural Networks, 1996, 7(2): 388-399.
  • 6Ge S S, Hang C C, Woon L C. Adaptive neural network control of robot manipulators in task space[J]. IEEE Transactions on Industrial Electronics, 1997, 44(6): 746-752.
  • 7Purwar S, Kar I N, Jha A N. Neuro sliding mode control of robotic manipulator[C]. IEEE Conference on Robotics, Automation and Mechatronics, Singapore, 2004.
  • 8Sun Fuchun, Sun Zengqi, Zhang R J, et al. Neural adaptive tracking controller for robot manipulators with unknown dynamics[J], IEE Proceedings-Control Theory and Applications, 2000, 147(3): 366-370.
  • 9Sun Fuchun, Li Hanxiong, Li Lei. Robot discrete adaptive control based on dynamic inversion using dynamical neural networks[J]. Automatica, 2002, 38(11): 1977-1983.
  • 10Jung S, Kim S S. Hardware implementation of a real-time neural network controller with a DSP and an FPGA for nonlinear systems [J]. IEEE Transactions on Industrial Electronics, 2007, 54(1): 265-271.

共引文献19

同被引文献190

引证文献19

二级引证文献61

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部