Risk-Augmented Loss With Attention Mechanisms: Enhancing Proximal Policy Optimization for Safer Autonomous Driving
IEEE Transactions on Intelligent Transportation Systems · 2026-08 · 27 (8) · 9364-9380
DOI: 10.1109/tits.2026.3687399 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-08. Verfasst von Safae Belkhyr und 2 weiteren Autor:innen. Die Arbeit nennt 51 Literaturangaben. Gefördert von: National Center for Scientific and Technical Research of Morocco (CNRST) through the Ph.D.-Associate Scholarship—PASS.
Abstract (Originalsprache)
Autonomous driving (AD) on highways presents significant challenges due to dynamic environments, high speeds, and uncertainties arising from sensor noise or abrupt vehicle behavior. This paper explores enhancing decision-making for autonomous vehicles (AVs) using an improved Proximal Policy Optimization (PPO) based on Deep Reinforcement Learning (DRL). The improvement is achieved through a novel risk-augmented loss function. Additionally, attention mechanisms are integrated to enhance performance. Unlike traditional approaches embedding risk in reward functions, our method integrates probabilistic risk assessment directly into the Proximal Policy Optimization (PPO) algorithm’s loss function, ensuring a clear separation between safety and performance objectives. Adaptive and robust decision-making are realized by paying more attention to important driving characteristics and punishing unsafe actions with risk-augmented loss. The experimental results show successes in safety, efficiency, and stability, proving that the proposed approach is effective in realistic highway driving scenarios. This system allows us to develop AV technology and address some of its major hurdles like dynamic environments, reliability and safety.
Förderung
- National Center for Scientific and Technical Research of Morocco (CNRST) through the Ph.D.-Associate Scholarship—PASS
Zitieren
APA
Belkhyr, S., Boumhidi, J., & Nikolov, N. S. (2026). Risk-Augmented Loss With Attention Mechanisms: Enhancing Proximal Policy Optimization for Safer Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems, 27(8), 9364-9380. https://doi.org/10.1109/tits.2026.3687399
Vancouver
Belkhyr S, Boumhidi J, Nikolov NS. Risk-Augmented Loss With Attention Mechanisms: Enhancing Proximal Policy Optimization for Safer Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems. 2026;27(8):9364-9380. doi:10.1109/tits.2026.3687399
BibTeX
@article{Belkhyr2026,
author = {Belkhyr, Safae and Boumhidi, Jaouad and Nikolov, Nikola S.},
title = {Risk-Augmented Loss With Attention Mechanisms: Enhancing Proximal Policy Optimization for Safer Autonomous Driving},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {8},
pages = {9364--9380},
doi = {10.1109/tits.2026.3687399}
}
EUVIMED