Adaptive Sliding Mode Disturbance Observer and Deep Reinforcement Learning Based Motion Control for Micropositioners

Liang, Shiyun1,2; Xi, Ruidong1,2; Xiao, Xiao3; Yang, Zhixin1,2

2022-03-01

10.3390/mi13030458

MICROMACHINES   影响因子和分区

2072-666X

The motion control of high-precision electromechanitcal systems, such as micropositioners, is challenging in terms of the inherent high nonlinearity, the sensitivity to external interference, and the complexity of accurate identification of the model parameters. To cope with these problems, this work investigates a disturbance observer-based deep reinforcement learning control strategy to realize high robustness and precise tracking performance. Reinforcement learning has shown great potential as optimal control scheme, however, its application in micropositioning systems is still rare. Therefore, embedded with the integral differential compensator (ID), deep deterministic policy gradient (DDPG) is utilized in this work with the ability to not only decrease the state error but also improve the transient response speed. In addition, an adaptive sliding mode disturbance observer (ASMDO) is proposed to further eliminate the collective effect caused by the lumped disturbances. The micropositioner controlled by the proposed algorithm can track the target path precisely with less than 1 mu m error in simulations and actual experiments, which shows the sterling performance and the accuracy improvement of the controller.

micropositioners reinforcement learning disturbance observer deep deterministic policy gradient

SCI ; EI

英语

其他

Science and Technology Development Fund, Macau SAR["0018/2019/AKP","SKL-IOTSC(UM)-2021-2023"] ; Ministry of Science and Technology of China[2019YFB1600700] ; Guangdong Science and Technology Department["2018B030324002","2020B1515130001"] ; Zhuhai Science and Technology Innovation Bureau[ZH22017002200001PWC] ; Jiangsu Science and Technology Department[BZ2021061] ; University of Macau[MYRG2020-00253-FST]

Chemistry ; Science & Technology - Other Topics ; Instruments & Instrumentation ; Physics

Chemistry, Analytical ; Nanoscience & Nanotechnology ; Instruments & Instrumentation ; Physics, Applied

WOS:000774082500001

MDPI

20221411911891

Motion control ; Reinforcement learning ; Transient analysis

Ergonomics and Human Factors Engineering:461.4 ; Artificial Intelligence:723.4 ; Specific Variables Control:731.3

Web of Science

1.Univ Macau, State Key Lab Internet Things Smart City, Macau 999078, Peoples R China
2.Univ Macau, Dept Electromech Engn, Macau 999078, Peoples R China
3.Southern Univ Sci & Technol, Dept Elect & Elect Engn, Shenzhen 518055, Peoples R China

Liang, Shiyun,Xi, Ruidong,Xiao, Xiao,et al. Adaptive Sliding Mode Disturbance Observer and Deep Reinforcement Learning Based Motion Control for Micropositioners[J]. MICROMACHINES,2022,13(3).

Liang, Shiyun,Xi, Ruidong,Xiao, Xiao,&Yang, Zhixin.(2022).Adaptive Sliding Mode Disturbance Observer and Deep Reinforcement Learning Based Motion Control for Micropositioners.MICROMACHINES,13(3).

Liang, Shiyun,et al."Adaptive Sliding Mode Disturbance Observer and Deep Reinforcement Learning Based Motion Control for Micropositioners".MICROMACHINES 13.3(2022).