Safe reinforcement learning for autonomous driving requires balancing safety constraints with driving efficiency. This paper proposes an adaptive constraint regulation framework for human preference-aware safe reinforcement learning in highway on-ramp merging scenarios. The method dynamically adjusts constraint limits according to traffic conditions and driver risk preferences, combined with an action shielding mechanism that filters unsafe decisions before execution. A hierarchical architecture separates high-level maneuver decisions from low-level model predictive control, ensuring both safety compliance and driving efficiency. Simulation experiments across varying traffic densities demonstrate that the proposed approach achieves a superior safety–efficiency trade-off compared to fixed-constraint baselines, maintaining collision-free merging while improving travel efficiency.
@article{teng2026adaptive,title={Adaptive Constraint Regulation for Human Preference-Aware Safe Reinforcement Learning of On-Ramp Merging},author={Teng, Jingjia and Huang, Wenjie and Yuan, Shijie and Hu, Manjiang and Qin, Hongmao and Li, Yang and Bian, Yougang and Li, Bai},journal={Machines},volume={14},number={6},pages={605},year={2026},month=may,publisher={MDPI},doi={10.3390/machines14060605},}
2022
Space Discretization-Based Optimal Trajectory Planning for Automated Vehicles in Narrow Corridor Scenes
Biao Xu, Shijie Yuan, Xuerong Lin, and 3 more authors
Autonomous vehicles operating in narrow corridor scenarios face challenging motion planning problems with tight spatial constraints. This paper presents a space-discretization-based optimal trajectory planning method for automated vehicles in narrow corridors. The approach formulates the planning problem as a quadratic programming optimization that incorporates vehicle kinematic constraints, boundary constraints, comfort requirements, and driving efficiency objectives within a discretized space representation. The method generates smooth, dynamically feasible trajectories that safely navigate constrained environments while optimizing for passenger comfort and travel time. The proposed framework is validated through extensive simulations and real-world field experiments, demonstrating reliable trajectory generation in various narrow-corridor configurations.
@article{xu2022space,title={Space Discretization-Based Optimal Trajectory Planning for Automated Vehicles in Narrow Corridor Scenes},author={Xu, Biao and Yuan, Shijie and Lin, Xuerong and Hu, Manjiang and Bian, Yougang and Qin, Zhaobo},journal={Electronics},volume={11},number={24},pages={4239},year={2022},month=dec,publisher={MDPI},doi={10.3390/electronics11244239},}