Deep Reinforcement Learning Enabled Decision-Making for Autonomous Driving at Intersections
- PDF / 3,748,939 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 9 Downloads / 199 Views
Deep Reinforcement Learning Enabled Decision‑Making for Autonomous Driving at Intersections Guofa Li1,2 · Shenglong Li1 · Shen Li3 · Yechen Qin4 · Dongpu Cao2 · Xingda Qu1 · Bo Cheng5 Received: 14 January 2020 / Accepted: 21 July 2020 / Published online: 13 November 2020 © China Society of Automotive Engineers (China SAE) 2020
Abstract Road intersection is one of the most complex and accident-prone traffic scenarios, so it’s challenging for autonomous vehicles (AVs) to make safe and efficient decisions at the intersections. Most of the related studies focus on the solution to a single scenario or only guarantee safety without considering driving efficiency. To address these problems, this study proposed a deep reinforcement learning enabled decision-making framework for AVs to drive through intersections automatically, safely and efficiently. The mapping relationship between traffic images and vehicle operations was obtained by an end-to-end decision-making framework established by convolutional neural networks. Traffic images collected at two timesteps were used to calculate the relative velocity between vehicles. Markov decision process was employed to model the interaction between AVs and other vehicles, and the deep Q-network algorithm was utilized to obtain the optimal driving policy regarding safety and efficiency. To verify the effectiveness of the proposed decision-making framework, the top three accident-prone crossing path crash scenarios at intersections were simulated, when different initial vehicle states were adopted for better generalization capability. The results showed that the developed method could make AVs drive safely and efficiently through intersections in all of the tested scenarios. Keywords Autonomous vehicles · Driving safety and efficiency · Intersection · Decision-making · Deep reinforcement learning Abbreviations AV Autonomous vehicle DQN Deep Q-network DRL Deep reinforcement learning LTAP/LD Left turn across path-lateral direction * Shen Li [email protected]
Guofa Li [email protected]; [email protected]
1
Institute of Human Factors and Ergonomics, College of Mechatronics and Control Engineering, Shenzhen University, Shenzhen 518060, China
2
Department of Mechanical and Mechatronics Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada
3
Department of Civil and Environmental Engineering, University of Wisconsin-Madison, Madison, WI 53706, USA
4
School of Mechanical Engineering, Beijing Institute of Technology, Beijing 100081, China
5
State Key Laboratory of Automotive Safety and Energy, School of Vehicle and Mobility, Tsinghua University, Beijing 100084, China
13
Vol:.(1234567890)
LTAP/OD Left turn across path-opposite direction MDP Markov decision process OV Other vehicle SCP Straight crossing path V2I Vehicle-to-infrastructure V2V Vehicle-to-vehicle
1 Introduction Autonomous driving is a topic widely concerned by scientific research institutions and enterprises because of its great potential in changing existing mobility and, most
Data Loading...
