Sep 2026· European Transport Research Review· Vol 18· 0 citations· 76 references
TL;DR
A scalable Vision-AI and deep learning framework modelling driver decisions based on vehicle type, speed, acceleration, lane occupation, and signal distance is presented, showcasing the model’s robustness and potential to improve intersection safety and inform intelligent traffic management.
Abstract
Driver behaviour in the dilemma zone critically influences red-light violations and intersection safety. This study presents a scalable Vision-AI and deep learning framework modelling driver decisions based on vehicle type, speed, acceleration, lane occupation, and signal distance. Validated at a signalised intersection in Thessaloniki, Greece, UAV-collected data yielded over 11,000 vehicle trajectories annotated with stop/go decisions during the yellow phase. A multi-layer perceptron classifier trained on this data reached 92.33% test accuracy and 91.76% F1-score. An ablation study analysed feature impacts, showcasing the model’s robustness and potential to improve intersection safety and inform intelligent traffic management.
The proposed framework improves the safety and crossing efficiency of autonomous vehicle decision-making at unsignalized intersections and introduces a composite prioritized replay mechanism into the Twin Delayed Deep Deterministic Policy Gradient algorithm.
Shufeng Wang, Yu-Hang Wang, Yongxin Lei et al.· Machines· 0 citations
While intelligent driving systems have achieved notable advances in perception, prediction, and motion planning, robust high-level decision-making remains a persistent challenge in long-tail scenarios that demand semantic scene understanding, contextual reasoning, and experience-based judgment. Rulebased policies tend...
Qiu-Man Xu, Shuai Zhao· 2026 3rd International Confe...· 0 citations
An integrated safety-control framework that combines real-world-data-driven behavior modeling with deep reinforcement learning to design longitudinal AV control strategies for mixed traffic containing aggressive human drivers is proposed.
Systematic scenario classification supports the characterization of test conditions in simulation-based autonomous driving validation. This paper proposes a multi-task framework that combines OpenSCENARIO text embeddings with Ego-vehicle motion representations learned by Autoencoders trained on the SinD real-world data...
Sungmo Ku, Jin-Ho Lee· ISPRS International Journal...· 0 citations
Navigating unregulated intersections with a heavy vehicle is a challenging task harboring significant risks for the vehicle itself and other traffic participants. In this study we introduce a dynamic, evidence-based risk assessment algorithm predicting increased general risk at upcoming intersections based on environme...
Joe Steinhauer, Andreas Absér, Yacine Atif et al.· Adjunct Proceedings of the 1...· 0 citations
A Dual Neural-Calibrated Interacting Multiple Model (DNC-IMM) that improves adaptability to driving context while preserving the probabilistic structure and interpretability of a conventional IMM is proposed.
Woong-Chan Byun, Seung-Hyun Kong· The Journal of The Korea Ins...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
