Deep adaptive control with online identification for industrial robots

Shen，Tan1; Qiao，Xue Chun1; Dong，Yun Long1; Wang，Yu Ran2; Zhang，Wei2; Yuan，Ye1

2022

10.1007/s11431-022-2183-7

Science China-Technological Sciences   Impact Factor & Quartile

1674-7321

1869-1900

Derivation of control equations from data is a critical problem in numerous scientific and engineering fields. The inverse dynamic control of robot manipulators in the field of industrial robot research is a key example. Traditionally, researchers needed to obtain the robot dynamic model through physical modeling methods before developing controllers. However, the robot dynamic model and suitable control methods are often elusive and difficult to tune, particularly when dealing with real dynamical systems. In this paper, we combine an enhanced online sparse Bayesian learning (OSBL) algorithm and a model reference adaptive control method to obtain a data-driven modeling and control strategy from data containing noise; this strategy can be applied to dynamical systems. In particular, we use a sparse Bayesian approach, relying only on some prior knowledge of its physics, to extract an accurate mechanistic model from the measured data. Unmodeled parameters are further identified from the modeling error through a deep neural network (DNN). By combining the identification model with a model reference adaptive control approach, a general deep adaptive control (DAC) method is obtained, which can tolerate unmodeled dynamics. The adaptive update law is derived from Lyapunov’s stability criterion, which guarantees the asymptotic stability of the system. Finally, the Enhanced OSBL identification method and DAC scheme are applied on a six-degree-of-freedom industrial robot, and the effectiveness of the proposed method is verified.

adaptive control industrial robots online identification sparse Bayesian learning

SCI

English

Others

National Natural Science Foundation of China[52188102]

Engineering ; Materials Science

Engineering, Multidisciplinary ; Materials Science, Multidisciplinary

WOS:000870595600001

SCIENCE PRESS

2-s2.0-85140262609

Scopus

1.School of Artificial Intelligence and Automation,Huazhong University of Science and Technology,Wuhan,430074,China
2.Department of Mechanical and Energy Engineering,Southern University of Science and Technology,Shenzhen,518055,China

Shen，Tan,Qiao，Xue Chun,Dong，Yun Long,et al. Deep adaptive control with online identification for industrial robots[J]. Science China-Technological Sciences,2022.

Shen，Tan,Qiao，Xue Chun,Dong，Yun Long,Wang，Yu Ran,Zhang，Wei,&Yuan，Ye.(2022).Deep adaptive control with online identification for industrial robots.Science China-Technological Sciences.

Shen，Tan,et al."Deep adaptive control with online identification for industrial robots".Science China-Technological Sciences (2022).