| Model-Free Recurrent Reinforcement Learning for AUV Horizontal Control | |
Huo YJ(霍雨佳)1,2 ; Li YP(李一平)1; Feng XS(封锡盛)1
| |
| Department | 水下机器人研究室 |
| Conference Name | 2018 3rd International Conference on Automation, Control and Robotics Engineering, CACRE 2018 |
| Conference Date | July 19, 2018 - July 22, 2018 |
| Conference Place | Chengdu, China |
| Source Publication | 3rd International Conference on Automation, Control and Robotics Engineering, CACRE 2018 |
| Publisher | IOP PUBLISHING LTD |
| Publication Place | BRISTOL, ENGLAND |
| 2018 | |
| Pages | 1-8 |
| Indexed By | EI ; CPCI（ISTP） |
| EI Accession number | 20184205940937 |
| WOS ID | WOS:000467866100063 |
| Contribution Rank | 1 |
| ISSN | 1757-8981 |
| Abstract | In this paper, aiming at the problems of 2-DOF horizontal motion control with high precision for autonomous underwater vehicle(AUV) trajectory tracking tasks, deep reinforcement learning controllers are applied to these conditions. These control problems are considered as a POMDP (Partially Observable Markov Decision Process). Model-free reinforcement learning(RL) algorithms for continuous control mission based on Deterministic Policy Gradient(DPG) allows robots learn from received delayed rewards when interacting with environments. Recurrent neural networks LSTM (Long Short-Term Memory) are involved into the reinforcement learning algorithm. Through this deep reinforcement learning algorithm, AUVs learn from sequences of dynamic information. The horizontal trajectory tracking tasks are described by LOS method and the motion control are idealized as a SISO model. Tanh-estimators are presented as data normalization. Moreover, AUV horizontal trajectory tracking and motion control simulation results demonstrate this algorithm gets better accuracy compared with the PID method and other non-recurrent methods. Efforts show the efficiency and effectiveness of the improved deep reinforcement learning algorithm. |
| Language | 英语 |
| Citation statistics | |
| Document Type | 会议论文 |
| Identifier | http://ir.sia.cn/handle/173321/23428 |
| Collection | 水下机器人研究室 |
| Corresponding Author | Huo YJ(霍雨佳) |
| Affiliation | 1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 2.University of Chinese, Academy of Sciences, Beijing 100049, China |
| Recommended Citation GB/T 7714 | Huo YJ,Li YP,Feng XS. Model-Free Recurrent Reinforcement Learning for AUV Horizontal Control[C]. BRISTOL, ENGLAND:IOP PUBLISHING LTD,2018:1-8. |
| Files in This Item: | ||||||
| File Name/Size | DocType | Version | Access | License | ||
| Model-Free Recurrent（692KB） | 会议论文 | 开放获取 | CC BY-NC-SA | View Application Full Text | ||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment