SAFE-AD: Socially aware field-enhanced reinforcement learning for autonomous driving in interactive traffic
Communications in Transportation Research · 06.11.2026
DOI: 10.26599/commtr.2026.9640067 ↗Kurz gefasst
Fachartikel in der Zeitschrift Communications in Transportation Research, online erschienen am 06.11.2026. Verfasst von Zian Wang und 8 weiteren Autor:innen.
Abstract (Originalsprache)
An autonomous vehicle can complete its route while disrupting surrounding traffic. We introduce SAFE-AD, augmenting reinforcement learning (RL) observations with compact descriptors of a finite-horizon interaction-pressure field constructed from current traffic states. The complete objective supplements the environment's task reward with risk, comfort, and externality costs. Then, we formulate a context-conditioned physics-informed neural network (PINN) to approximate the numerical field. Evaluation combines held-out naturalistic recordings, HighwayEnv diagnostics, and closed-loop MetaDrive tests in various traffic scenarios, with a matched factorial experiment with continuous soft actor-critic (SAC) separates observation and objective effects. At unprotected intersections, the complete profile reduces collision rate from 0.296 to 0.220 and mean absolute jerk by 0.98 m/s3 relative to baseline SAC. Besides, the mean absolute jerk in roundabout decreases by 1.54 m/s3. The results show scenario-specific gains and sensitivity to objective calibration.
Zitieren
APA
Wang, Z., Huang, W., Deng, Z., Shu, Y., Xu, J., Wang, Y., Li, S., Cao, D., & Sun, C. (2026). SAFE-AD: Socially aware field-enhanced reinforcement learning for autonomous driving in interactive traffic. Communications in Transportation Research. https://doi.org/10.26599/commtr.2026.9640067
Vancouver
Wang Z, Huang W, Deng Z, Shu Y, Xu J, Wang Y, et al. SAFE-AD: Socially aware field-enhanced reinforcement learning for autonomous driving in interactive traffic. Communications in Transportation Research. 2026. doi:10.26599/commtr.2026.9640067
BibTeX
@article{Wang2026,
author = {Wang, Zian and Huang, Wenjie and Deng, Zejian and Shu, Yiming and Xu, Jiahui and Wang, Yong and Li, Shen and Cao, Dongpu and Sun, Chen},
title = {SAFE-AD: Socially aware field-enhanced reinforcement learning for autonomous driving in interactive traffic},
journal = {Communications in Transportation Research},
year = {2026},
doi = {10.26599/commtr.2026.9640067}
}
EUVIMED