Citation

Chen J, Sun D, Zhao M. IEEE Trans. Intel. Transp. Syst. 2023; 24(2): 1609-1618.

Copyright

(Copyright © 2023, IEEE (Institute of Electrical and Electronics Engineers))

DOI

10.1109/TITS.2022.3222492

PMID

unavailable

Abstract

Safely and efficiently completing unprotected left turns at intersections is challenging for both automated vehicles and human drivers, given that it is hard to predict the intentions of other road users. Currently, automated vehicles are inclined to adopt an overly conservative policy for safety reasons. And experienced drivers respond to right-of-way competition by employing "negotiation" skills to improve efficiency, mainly through steering, braking and acceleration. However, negotiations do not always go smoothly, and a phenomenon similar to "pedestrian face-off" is called "vehicle face-off", specifically speaking, this host vehicle and vehicles involved in the competition perform the same maneuvers (acceleration or deceleration) continuously and simultaneously, leading to reduced efficiency and safety. In this paper, a new deep reinforcement learning (DRL) method is proposed based on deep convolutional fuzzy systems (DCFS) for automated vehicles to deal with unprotected left-turn scenarios on urban roads. A total of 30 subjects participated in the experiment, and the results show that the proposed method can provide human-like driving skills for automated vehicles, and effectively avoid "vehicle face-off" to improve the efficiency of unprotected left turns on the premise of ensuring safety.

Language: en

Keywords

Deep learning; deep reinforcement learning; human-like driving policy; LTAP/OD; Reinforcement learning; Roads; Safety; Turning; TV; Vehicle face-off; Vehicles