Personalized Car-Following Control Based on a Hybrid of Reinforcement Learning and Supervised Learning
With the development of intelligent vehicles, more research has focused on achieving human-like driving. As an important component of intelligent vehicle control, car-following control should ensure safety, tracking, comfort while considering the acceptance of human drivers. In this paper, we propos...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on intelligent transportation systems 2023-06, Vol.24 (6), p.1-16 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | With the development of intelligent vehicles, more research has focused on achieving human-like driving. As an important component of intelligent vehicle control, car-following control should ensure safety, tracking, comfort while considering the acceptance of human drivers. In this paper, we propose a car-following control strategy \bm{\pi}_{\bm{Hybrid}} based on a hybrid of reinforcement learning (RL) and supervised learning (SL). RL is used to achieve multi-objective collaborative optimization in car-following control, and SL is used to achieve human like car-following. Through the complementary advantages of the two learning methods, \bm{\pi}_{{Hybrid}} can achieve high performance car-following while matching the personalized car-following characteristics of human drivers. RL is used as the main framework of \bm{\pi}_{{Hybrid}} . In addition, the personalized car-following reference model (PCRM) of human drivers based on Gaussian mixture regression, and the motion uncertainty model of preceding vehicle (MUMPV) based on the sequence-to-sequence network are established and incorporated into the RL framework. PCRM can lead \bm{\pi }_{{Hybrid}} to learn the different characteristics of human drivers, and improve the anthropomorphism of \bm{\pi }_{{Hybrid}} ; MUMPV enables \bm{\pi }_{{Hybrid}} to consider the dynamic changes of the traffic environment and to become more robust. \bm{\pi }_{{Hybrid}} is trained and tested on High D dataset, and the generalizability verification is based on the self-built real vehicle data collection platform. The results show that \bm{\pi }_{{Hybrid}} can match human drivers' personalized car-following characteristics and can outperform human drivers in safety, comfort, and tracking of the preceding vehicle. |
---|---|
ISSN: | 1524-9050 1558-0016 |
DOI: | 10.1109/TITS.2023.3245362 |