南方科技大学知识苑(SUSTech KC): A Deep Q-Network for robotic odor/gas source localization: Modeling, measurement and comparative study

题名	A Deep Q-Network for robotic odor/gas source localization: Modeling, measurement and comparative study
作者	Chen, Xinxing1,2,3 ; Fu, Chenglong2,3 ; Huang, Jian 1
通讯作者	Huang, Jian
发表日期	2021-10-01
DOI	10.1016/j.measurement.2021.109725
发表期刊	MEASUREMENT 影响因子和分区
ISSN	0263-2241
EISSN	1873-412X
卷号	183
摘要	Robotic odor/gas source localization is a widely studied field, but most of the existing works are about rule-based algorithms. In this paper, the Deep Q-Network algorithm is applied to solve the odor source localization problem. An odor hits distribution model is proposed to model the odor concentration distribution in indoor environments, taking the dispersion by airflow, the odor molecular random walk, and the obstacles into account. The Deep Q-Network takes the stacked historic measurement data as the input and outputs the expected cumulative future reward of actions of the robots. The network is trained through 35,000 repeated episodes of random odor source localization tasks. The Deep Q-Network method is evaluated under four different environment settings in a simplified simulator and compared with two widely used odor source localization algorithms. The evaluation results demonstrate the advantages of the proposed algorithm. The algorithm is also validated in more complex indoor environments.
关键词	Olfactory robot Odor source localization Deep Q-Network Obstacle avoidance Action policy
相关链接	[来源记录]
收录类别	SCI ; EI
语种	英语
学校署名	其他
资助项目	Fundamental Research Funds for the Central Universities["HUST: 2019kfyRCPY","2019kfyXKJC019"] ; Research Fund of PLA of China[BWS17J024] ; Science, Technology and Innovation Commission of Shenzhen Municipality[ZDSYS20200811143601004]
WOS研究方向	Engineering ; Instruments & Instrumentation
WOS类目	Engineering, Multidisciplinary ; Instruments & Instrumentation
WOS记录号	WOS:000693561300004
出版者	ELSEVIER SCI LTD
EI入藏号	20212710587020
EI主题词	Electronic nose ; Odors ; Robotics
EI分类号	Robotics:731.5 ; Chemistry:801 ; Accidents and Accident Prevention:914.1 ; Electric and Electronic Instruments:942.1
ESI学科分类	ENGINEERING
来源库	Web of Science
引用统计	被引频次[WOS]：19
成果类型	期刊论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/245883
专题	南方科技大学工学院_机械与能源工程系
作者单位	1.Huazhong Univ Sci & Technol, Sch Artificial Intelligence & Automat, Key Lab Minist Educ Image Proc & Intelligent Cont, Wuhan 430074, Peoples R China 2.Shenzhen Key Lab Biomimet Robot & Intelligent Sys, Shenzhen 518055, Peoples R China 3.Southern Univ Sci & Technol, Guangdong Prov Key Lab Human Augmentat, Rehabil Robot Univ, Shenzhen 518055, Peoples R China
第一作者单位	南方科技大学
推荐引用方式 GB/T 7714	Chen, Xinxing,Fu, Chenglong,Huang, Jian. A Deep Q-Network for robotic odor/gas source localization: Modeling, measurement and comparative study[J]. MEASUREMENT,2021,183.
APA	Chen, Xinxing,Fu, Chenglong,&Huang, Jian.(2021).A Deep Q-Network for robotic odor/gas source localization: Modeling, measurement and comparative study.MEASUREMENT,183.
MLA	Chen, Xinxing,et al."A Deep Q-Network for robotic odor/gas source localization: Modeling, measurement and comparative study".MEASUREMENT 183(2021).