Chenxi Xu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Chenxi Xu has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Haibo Wu
School of Computer Science, Northwestern Polytechnical University, 26487 Xi'an, Shaanxi China
1 shared publication - Haobin Shi
Northwestern Polytechnical University
1 shared publication - Jinhui Zhu
School of Computer Science, Northwestern Polytechnical University, 26487 Xi'an, Shaanxi China 710072
1 shared publication - Kao-Shing Hwang
the Department of Electrical Engineering, National Sun Yat-sen University, Kaohsiung, Taiwan
1 shared publication - Maxwell Hwang
School of Medicine, zhe jiang da xue, 12377 Hangzhou, Zhejiang China
1 shared publication
Latest Publications
- 29 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 28 (12) , 3244-3255
Adaptive Image-Based Visual Servoing Using Reinforcement Learning With Fuzzy State Coding
Image-Based Visual Servoing (IBVS) allows precise control of positioning and motion for relatively stationary targets using visual feedback. For IBVS, a mixture parameter β allows better approximation of the image Jacobian matrix, which has a significant effect on the performance of IBVS. However, the setting for the mixture parameter depends on the camera's real-time posture, there is no clear way to define the change rules for most IBVS applications. Using simple model-free reinforcement learning (RL), Q-Learning, this study proposes a method to adjust the image Jacobian matrix for IBVS adaptively. If the state space is discretized, traditional Q-learning encounters problems with the resolution that can cause sudden changes in the action, so the visual servoing system performs poorly. Besides, a robot in a real-world environment also cannot learn on as large a scale as virtual agents, so the efficiency with which agents learn must be increased. This study proposes a method that uses Fuzzy State Coding to accelerate learning during the training phase and to produce a smooth output in the application phase of the learning experience. A method that compensates for delay also allows more accurate extraction of features in a real environment. The results for simulation and experiment demonstrate that the proposed method performs better than other methods, in terms of learning speed, movement trajectory, and convergence time.
- 29 April 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Fuzzy Systems
- Vol. 28 (12) , 3244-3255
Adaptive Image-Based Visual Servoing Using Reinforcement Learning With Fuzzy State Coding
Image-Based Visual Servoing (IBVS) allows precise control of positioning and motion for relatively stationary targets using visual feedback. For IBVS, a mixture parameter β allows better approximation of the image Jacobian matrix, which has a significant effect on the performance of IBVS. However, the setting for the mixture parameter depends on the camera's real-time posture, there is no clear way to define the change rules for most IBVS applications. Using simple model-free reinforcement learning (RL), Q-Learning, this study proposes a method to adjust the image Jacobian matrix for IBVS adaptively. If the state space is discretized, traditional Q-learning encounters problems with the resolution that can cause sudden changes in the action, so the visual servoing system performs poorly. Besides, a robot in a real-world environment also cannot learn on as large a scale as virtual agents, so the efficiency with which agents learn must be increased. This study proposes a method that uses Fuzzy State Coding to accelerate learning during the training phase and to produce a smooth output in the application phase of the learning experience. A method that compensates for delay also allows more accurate extraction of features in a real environment. The results for simulation and experiment demonstrate that the proposed method performs better than other methods, in terms of learning speed, movement trajectory, and convergence time.