Vision-based neural predictive tracking control for multi-manipulator systems with parametric uncertainty. (April 2021)

• Record Type: Journal Article
• Authors: Wu, Jinhui; Jin, Zhehao; Liu, Andong; Yu, Li
• Is Part Of: ISA transactions. Volume 110(2021)
• Page Start: 247
• Page End: 257
• Publication Date: 2021-04
• Subjects: Image-based visual servoing -- Parametric uncertainty -- Recurrent neural network -- Model predictive control -- Input-to-state practical stability -- Extended state observer; Engineering instruments -- Periodicals; Engineering instruments; Periodicals; Electronic journals; 629.805
• DOI: 10.1016/j.isatra.2020.10.057
• Languages: English
• ISSNs: 0019-0578

Abstract

Abstract: To deal with the coordination problem for multi-manipulator trajectory tracking systems with parametric uncertainties, this paper proposes a two-layer control scheme incorporating a model predictive strategy and an extended state observer. In the kinematic layer, the visual information is implemented and a visual servoing error model is derived by the image-based visual servoing strategy. A recurrent neural network model predictive control approach is proposed to obtain velocities which are regarded as the reference signals for the dynamic layer. For dynamics, a linear time-varying dynamic model of the multi-manipulator system coupled with the object is established, where the parametric uncertainty is recognized as an added disturbance. An extended state observer is sequentially designed to estimate the disturbance by using pole placement method. The input-to-state practical stability of the system is further analyzed with a bounded disturbance. Finally, simulations and comparison are given to verify the effectiveness and robustness of the proposed algorithm. Highlights: The kinematics and dynamics for visual servoing systems of the multi-manipulator are modeled. A two-layer control scheme is proposed to handle the coordination problem for trajectory tracking systems of the multi-manipulator. A model predictive controller combined with a recurrent neural network and an extended state observer is used to solve the optimization problem. The input-to-state practical stability of the system and the maximal admissible bound of the uncertainty are given.