Trajectory Prediction-Aided Deep Reinforcement Learning for Autonomous Vehicle Decision-Making at Unsignalized Intersections
Machines · 06.08.2026 · 14 (8) · 900
DOI: 10.3390/machines14080900 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machines, online erschienen am 06.08.2026. Verfasst von Shufeng Wang und 3 weiteren Autor:innen. Die Arbeit nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: State Key Lab of Intelligent Transportation System, Key Research and Development Program of Shandong Province, Postgraduate Quality Professional Degree Teaching Case Base of Shandong Province.
Abstract (Originalsprache)
Due to the absence of traffic signal control and the difficulty in accurately estimating the future movements of surrounding vehicles, autonomous vehicle decision-making faces challenges at unsignalized intersections. This study proposes a trajectory prediction-aided deep reinforcement learning framework. First, a composite prioritized replay mechanism is introduced into the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm, jointly considering temporal-difference error and reward-based event severity to enhance critical-experience reuse. Second, a convolutional multi-layer long short-term memory (CM-LSTM) model predicts surrounding-vehicle trajectories through convolutional local-motion encoding and stacked LSTM temporal modeling, and the predicted trajectories are incorporated into the deep reinforcement learning state representation. A multi-objective reward function is designed to balance collision avoidance, passing efficiency, lane keeping, and task completion. In CARLA go-straight and left-turn tests, CLS-TD3 achieves success rates of 93.8% and 90.2%, collision rates of 2.5% and 4.2%, and average passing times of 5.18 s and 5.58 s. Compared with TD3, the success rates increase by 6.3 and 8.6 percentage points, while average passing times decrease by 18.8% and 20.5%. These results demonstrate that the proposed framework improves the safety and crossing efficiency of autonomous vehicle decision-making at unsignalized intersections.
Förderung
- State Key Lab of Intelligent Transportation System
- Key Research and Development Program of Shandong Province
- Postgraduate Quality Professional Degree Teaching Case Base of Shandong Province
Zitieren
APA
Wang, S., Wang, Y., Lei, Y., & Jin, L. (2026). Trajectory Prediction-Aided Deep Reinforcement Learning for Autonomous Vehicle Decision-Making at Unsignalized Intersections. Machines, 14(8), 900. https://doi.org/10.3390/machines14080900
Vancouver
Wang S, Wang Y, Lei Y, Jin L. Trajectory Prediction-Aided Deep Reinforcement Learning for Autonomous Vehicle Decision-Making at Unsignalized Intersections. Machines. 2026;14(8):900. doi:10.3390/machines14080900
BibTeX
@article{Wang2026,
author = {Wang, Shufeng and Wang, Yuhang and Lei, Yongxin and Jin, Lu},
title = {Trajectory Prediction-Aided Deep Reinforcement Learning for Autonomous Vehicle Decision-Making at Unsignalized Intersections},
journal = {Machines},
year = {2026},
volume = {14},
number = {8},
pages = {900},
doi = {10.3390/machines14080900}
}
EUVIMED