期刊
NEUROCOMPUTING
卷 402, 期 -, 页码 384-394出版社
ELSEVIER
DOI: 10.1016/j.neucom.2020.03.049
关键词
Image-based visual servoing (IBVS); Extreme learning machine (ELM); Reinforcement learning; Q-Learning; Robot
资金
- National Natural Science Foundation of China [61873056, 61621004, 61420106016]
- Fundamental Research Funds for the Central Universities in China [N2004001, N2004002, N182608004]
- Research Fund of State Key Laboratory of Synthetical Automation for Process Industries in China [2013ZCX01]
In this paper, a novel image-based visual servoing (IBVS) method using Extreme Learning Machine (ELM) and Q-learning is proposed to solve the problems of complex modeling and selection of the servo gain. First, the pseudoinverse of the interaction matrix is approached by ELM which avoids the singularity of the interaction matrix effectively and is robust to interferences such as feature noises and camera calibration errors. Second, a reinforcement learning method, Q-learning, is adopted to adaptively adjust the servo gain in order to improve the convergence speed and stability. Compared with other methods, ELM has better generalization performance, faster operation speed and a unique optimal solution. Also, Q-learning has self-learning ability without experience in advance. The effectiveness of the proposed method is validated by simulations and experiment on a 6-DOF robot with eye-in-hand configuration. (C) 2020 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据