|
|||||
|
|
Adaptive visual servoing for the robot manipulator with extreme learning machine and reinforcement learning |
|
| Authors: | Jiashuai Li Xiuyan Peng Bing Li Victor Sreeram Jiawei Wu Wansheng Mi |
| Affiliation: | 1. College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China;2. College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China
Contribution: Conceptualization, Formal analysis, Funding acquisition, ?Investigation, Project administration, Resources, Supervision;3. School of Electrical, Electronic, and Computer Engineering, The University of Western Australia, Crawley, Australia;4. College of Intelligent Systems Science and Engineering, Harbin Engineering University, Harbin, China Contribution: Conceptualization, Formal analysis, ?Investigation, Methodology, Resources, Visualization;5. Department of Steam Power, 703 Research Institute of CSSC, Harbin, China Contribution: Conceptualization, Formal analysis, ?Investigation, Methodology, Resources, Visualization |
| Abstract: | In this study, a novel image-based visual servo (IBVS) controller for robot manipulators is investigated using an optimized extreme learning machine (ELM) algorithm and an offline reinforcement learning (RL) algorithm. First of all, the classical IBVS method and its difficulties in accurately estimating the image interaction matrix and avoiding the singularity of pseudo-inverse are introduced. Subsequently, an IBVS method based on ELM and RL is proposed to solve the problem of the singularity of the pseudo-inverse solution and tune adaptive servo gain, improving the servo efficiency and stability. Specifically, the ELM algorithm optimized by particle swarm optimization (PSO) was used to approximate the pseudo-inverse of the image interaction matrix to reduce the influence of camera calibration errors. Then, the RL algorithm was adopted to tune the adaptive visual servo gain in continuous space and improve the convergence speed. Finally, comparative simulation experiments on a 6-DOF robot manipulator were conducted to verify the effectiveness of the proposed IBVS controller. |
| Keywords: | extreme learning machine image-based visual servoing particle swarm optimization reinforcement learning robot manipulator |