Model-Free Recurrent Reinforcement Learning for AUV Horizontal Control

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 水下机器人研究室

	Model-Free Recurrent Reinforcement Learning for AUV Horizontal Control
	Feng XS(封锡盛)2 ; Li YP(李一平)2 ; Huo YJ(霍雨佳)1,2
	2018
会议日期	July 19, 2018 - July 22, 2018
会议地点	Chengdu, China
页码	1-8
英文摘要	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.
产权排序	1
会议录	3rd International Conference on Automation, Control and Robotics Engineering, CACRE 2018
会议录出版者	IOP PUBLISHING LTD
会议录出版地	BRISTOL, ENGLAND
语种	英语
ISSN号	1757-8981
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/23428]
专题	沈阳自动化研究所_水下机器人研究室
作者单位	1.University of Chinese, Academy of Sciences, Beijing 100049, China 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China
推荐引用方式 GB/T 7714	Feng XS,Li YP,Huo YJ. Model-Free Recurrent Reinforcement Learning for AUV Horizontal Control[C]. 见:. Chengdu, China. July 19, 2018 - July 22, 2018.