Learning Driving Models From Parallel End-to-End Driving Data Set

doi:10.1109/JPROC.2019.2952735

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 平行智能技术与系统团队

	Learning Driving Models From Parallel End-to-End Driving Data Set
	Chen, Long 1,2; Wang, Qing 1,2; Lu, Xiankai 3; Cao, Dongpu 2,4; Wang, Fei-Yue5
发表期刊	PROCEEDINGS OF THE IEEE
ISSN	0018-9219
	2020-02-01
卷号	108 期号:2 页码:262-273
通讯作者	Wang, Fei-Yue(feiyue@ieee.org)
摘要	Parallel end-to-end driving aims to improve the performance of end-to-end driving models using both simulated- and real-world data. However, how to efficiently utilize the data from both the simulated world and the real world remains a difficult issue, since these data are usually not well aligned. In this article, we build a data set called the parallel end-to-end driving data set (PED) for parallel end-to-end driving research. PED consists of 13 000 images from the simulated world and 13 000 images from the real world that are used to train the model, as well as 2700 images from the real world that are used to test the model. The simulated-world data in PED are constructed according to the real world, and each simulated-world image corresponds to a real-world image. PED also contains the vehicle measurement data (GPS, speed, steering angle, and heading direction of the vehicle) related to both the simulated- and real-world images, which are not available in some other data sets. We conduct two types of experiments to illustrate the effectiveness and the superiority of PED and explore some ways to mix the simulated-world data with the real-world data to improve the performance of end-to-end driving models.
关键词	Data models Training Adaptation models Task analysis Reinforcement learning Decision making Transforms Data set end-to-end driving parallel driving
DOI	10.1109/JPROC.2019.2952735
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61773414] ; National Natural Science Foundation of China[61790565] ; National Key Research and Development Program of China[2018YFB1305002] ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Key Research and Development Program of China[2018YFB1305002] ; National Natural Science Foundation of China[61790565] ; National Natural Science Foundation of China[61773414]
项目资助者	Intel Collaborative Research Institute for Intelligent and Automated Connected Vehicles (ICRI-IACV) ; National Key Research and Development Program of China ; National Natural Science Foundation of China
WOS研究方向	Engineering
WOS类目	Engineering, Electrical & Electronic
WOS记录号	WOS:000510677500005
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
七大方向——子方向分类	人工智能+交通
引用统计	被引频次：40[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/28619
专题	多模态人工智能系统全国重点实验室_平行智能技术与系统团队
通讯作者	Wang, Fei-Yue
作者单位	1.Sun Yat Sen Univ, Sch Data & Comp Sci, Guangzhou 510275, Peoples R China 2.VIPioneers HuiTuo Inc, Qingdao 266109, Peoples R China 3.Incept Inst Artificial Intelligence, Abu Dhabi, U Arab Emirates 4.Univ Waterloo, Dept Mech & Mechatron Engn, Waterloo, ON N2L 3G1, Canada 5.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Chen, Long,Wang, Qing,Lu, Xiankai,et al. Learning Driving Models From Parallel End-to-End Driving Data Set[J]. PROCEEDINGS OF THE IEEE,2020,108(2):262-273.
APA	Chen, Long,Wang, Qing,Lu, Xiankai,Cao, Dongpu,&Wang, Fei-Yue.(2020).Learning Driving Models From Parallel End-to-End Driving Data Set.PROCEEDINGS OF THE IEEE,108(2),262-273.
MLA	Chen, Long,et al."Learning Driving Models From Parallel End-to-End Driving Data Set".PROCEEDINGS OF THE IEEE 108.2(2020):262-273.