Optimization and Safety Control of Autonomous Driving Strategy Based on Adaptive Reward Signal
Unmanned Systems · 28.07.2026 · 1-17
DOI: 10.1142/s2301385028500458 ↗Kurz gefasst
Fachartikel in der Zeitschrift Unmanned Systems, online erschienen am 28.07.2026. Verfasst von Kai He.
Abstract (Originalsprache)
In order to improve the efficiency and safety of autonomous driving in complex traffic environments, this study proposes a hierarchical control framework based on an adaptive reward signal (AR-E-DQN) and an adaptive responsibility sensitive safety (ARSS) model. The experimental results show that the proposed method outperforms traditional methods under different traffic densities. In low-density scenes, the average speed of AR-E-DQN is 28.52[Formula: see text]m/s, the average reward is 48.63, and the collision rate is only 1.2%, significantly better than DQN’s 25.86[Formula: see text]m/s, 37.63, and 5.2%. In high-density scenes ([Formula: see text]), adaptive rewards can still maintain a speed of 24.76[Formula: see text]m/s and a low collision rate of 5.3%, while traditional fixed rewards can reduce the speed to 20.32[Formula: see text]m/s and increase the collision rate to 12.8%. Similarly, ARSS significantly outperforms traditional responsibility sensitive safety (RSS) in terms of safety control, reducing collision rates by over 50% at high densities. Research has shown that this method achieves a better balance between efficiency and safety, and has strong practicality.
Zitieren
APA
He, K. (2026). Optimization and Safety Control of Autonomous Driving Strategy Based on Adaptive Reward Signal. Unmanned Systems, 1-17. https://doi.org/10.1142/s2301385028500458
Vancouver
He K. Optimization and Safety Control of Autonomous Driving Strategy Based on Adaptive Reward Signal. Unmanned Systems. 2026:1-17. doi:10.1142/s2301385028500458
BibTeX
@article{He2026,
author = {He, Kai},
title = {Optimization and Safety Control of Autonomous Driving Strategy Based on Adaptive Reward Signal},
journal = {Unmanned Systems},
year = {2026},
pages = {1--17},
doi = {10.1142/s2301385028500458}
}
EUVIMED