A synergistic reinforcement learning-based framework design in driving automation

doi:10.1016/j.compeleceng.2022.107989

	A synergistic reinforcement learning-based framework design in driving automation
	Qi, Yuqiong 1,2; Hu, Yang 3; Wu, Haibin 1; Li, Shen 4; Ye, Xiaochun 1; Fan, Dongrui 1
	2022-07-01
发表期刊	COMPUTERS & ELECTRICAL ENGINEERING
ISSN	0045-7906
卷号	101 页码:15
摘要	Autonomous driving, which integrates artificial intelligence and the Internet of Things, has piqued the interest of both academics and industry because of its economic and societal benefits. Rigorous accuracy and latency requirements are important for autonomous driving safety. In order to achieve high computation performance in driving automation system, we propose in this paper a heterogeneous multicore AI accelerator (HMAI). At the same time, on the HMAI, how to allocate a large number of real-time tasks to different accelerators remains a notable problem that is worth considering. Theoretically, this problem is NP-complete, and always solved using heuristic-based and guided random-search-based algorithms. However, the global state of HMAI cannot be considered comprehensively in these algorithms, which usually leads to suboptimal allocations. In this paper, we propose FlexAI, a predictive and global scheduling mechanism on HMAI. Specifically, the proposed scheduling algorithm that is based upon deep reinforcement learning (RL). In order to evaluate the quality of strategies produced by RL agent and update the observation of the scheduling agent, two scheduling metrics are proposed: Global State Value (Gvalue), Matching Score (MS) which pays attention to the requirements of various tasks in driving automation system like emergency level. In the experimental, FlexAI achieves up to 80% execution time reduction and 99% resource utilization improvement compared with Min-min, ATA in heuristics, and genetic algorithms, simulated annealing in guided random-search-based algorithms, and unscheduled case.
关键词	Autonomous Driving Heterogeneous Multicore AI Accelerator Criteria Reinforcement Learning Scheduling
DOI	10.1016/j.compeleceng.2022.107989
收录类别	SCI
语种	英语
资助项目	National Natural Science Foundation of China[61732018] ; National Natural Science Foundation of China[61872335] ; National Natural Science Foundation of China[61802367] ; Strategic Priority Research Program of Chinese Academy of Sciences[XDC05000000] ; International Partnership Program of Chinese Academy of Sciences[171111KYSB20200002]
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Hardware & Architecture ; Computer Science, Interdisciplinary Applications ; Engineering, Electrical & Electronic
WOS记录号	WOS:000798074000002
出版者	PERGAMON-ELSEVIER SCIENCE LTD
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19585
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Qi, Yuqiong
作者单位	1.Chinese Acad Sci, Inst Comp Technol, SKLCA, Beijing, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China 3.Univ Texas Dallas, Elect Engn Dept, Dallas, TX USA 4.Natl Univ Singapore, Singapore, Singapore
推荐引用方式 GB/T 7714	Qi, Yuqiong,Hu, Yang,Wu, Haibin,et al. A synergistic reinforcement learning-based framework design in driving automation[J]. COMPUTERS & ELECTRICAL ENGINEERING,2022,101:15.
APA	Qi, Yuqiong,Hu, Yang,Wu, Haibin,Li, Shen,Ye, Xiaochun,&Fan, Dongrui.(2022).A synergistic reinforcement learning-based framework design in driving automation.COMPUTERS & ELECTRICAL ENGINEERING,101,15.
MLA	Qi, Yuqiong,et al."A synergistic reinforcement learning-based framework design in driving automation".COMPUTERS & ELECTRICAL ENGINEERING 101(2022):15.