Path planning of mobile robot based on improved DDQN

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 工业控制网络与系统研究室

	Path planning of mobile robot based on improved DDQN
	Yang, Yunxiao 1,2,3; Wang, Jun 1; Zhang HL(张华良)2,3; Dai, Shilong 2,3
	2021
会议日期	August 20-22, 2021
会议地点	Changsha, Virtual, China
页码	1-6
英文摘要	Aiming at the problem of overestimation and sparse rewards of deep Q network algorithm in mobile robot path planning in reinforcement learning, an improved algorithm HERDDQN is proposed. Through the deep convolutional neural network model, the original RGB image is used as input, and it is trained through an end-to-end method. The improved deep reinforcement learning algorithm and the deep Q network algorithm are simulated in the same two-dimensional environment. The experimental results show that the HERDDQN algorithm solves the problem of overestimation and sparse reward better than the DQN algorithm in terms of success rate and reward convergence speed, Which shows that the improved algorithm finds a better strategy than the DQN algorithm.
产权排序	1
会议录	2nd International Conference on Computer Vision and Data Mining, ICVDM 2021
会议录出版者	IOP
会议录出版地	Bristol, UK
语种	英语
ISSN号	1742-6588
WOS记录号	IOP:1742-6588-2024-1-012029
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/29774]
专题	沈阳自动化研究所_工业控制网络与系统研究室
通讯作者	Yang, Yunxiao
作者单位	1.School of Computer Science, Shenyang University of Chemical Technology, Shenyang 110142, China 2.Industrial Control Network and System Laboratory, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 3.Institudes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China
推荐引用方式 GB/T 7714	Yang, Yunxiao,Wang, Jun,Zhang HL,et al. Path planning of mobile robot based on improved DDQN[C]. 见:. Changsha, Virtual, China. August 20-22, 2021.