STTC-EFRL 强化学习框架提升自动驾驶车辆安全轨迹跟踪精度
Epigraph Form Reinforcement Learning-based Safe Trajectory Tracking Control for Connected and Autonomous Vehicles
用 epigraph min-max 代替拉格朗日乘子来处理安全约束，训练稳定性和跟踪精度都比常规 DRL 更好，还做了实车在环测试。做自动驾驶控制或安全强化学习的开发者值得看看这套思路。
论文提出 STT Control Epigraph Form RL（STTC-EFRL），一个面向 Connected and Autonomous Vehicles（CAVs）安全轨迹跟踪（STT）的强化学习框架。该方法将 STT 问题建模为 epigraph 形式的 min-max 优化问题，利用与 epigraph 相关的递减标量来调整策略梯度下降方向，避免拉格朗日 DRL 方法中乘子增大导致梯度幅值放大、训练不稳定的问题。
技术细节上，作者还开发了一种计算高效的 ray-casting 方法，用于计算多面体缩放因子以量化安全性。实验包括 Vehicle-in-the-Loop 实车在环测试，结果显示 STTC-EFRL 的跟踪精度高于非学习类基线方法，训练稳定性优于广泛使用的拉格朗日 DRL 方法，同时在车联网环境下满足安全要求。
对从事自动驾驶控制与强化学习结合的研究者来说，这项工作提供了一个替代拉格朗日约束处理的训练思路，其实车在环验证也比纯仿真结果更具参考价值。
Epigraph Form Reinforcement Learning-based Safe Trajectory Tracking Control for Connected and Autonomous Vehicles
Safe trajectory tracking (STT) aims to enable autonomous vehicles to follow a reference trajectory accurately while avoiding collisions. This problem is particularly challenging for Connected and Autonomous Vehicles (CAVs) in highly dynamic environments. Existing non-learning-based STT methods often use simplified vehicle and interaction models to meet real-time requirements, which may result in suboptimal tracking accuracy. Although Deep Reinforcement Learning (DRL) can help address this limitation, widely used Lagrangian DRL methods often suffer from unstable training because increasing Lagrange multipliers amplify policy-gradient magnitudes. To address these issues, we propose a novel reinforcement learning framework for STT, called STT Control Epigraph Form RL (STTC-EFRL). In this framework, the STT problem is formulated as an epigraph-form min-max optimization problem. Based on this formulation, we develop a learning mechanism that uses a decreasing scalar related to the epigraph to adjust the policy gradient descent direction without increasing the gradient magnitude, thereby improving training stability. We also develop a computationally efficient ray-casting method to compute a polyhedron scaling factor for safety quantification. Experimental results, including Vehicle-in-the-Loop tests, show that STTC-EFRL achieves higher tracking accuracy than the considered non-learning-based baseline and more stable training than widely used Lagrangian DRL methods, while satisfying safety requirements in connected environments.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中，该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线，反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括：强化学习、自动驾驶、STTC-EFRL、安全控制，读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明：本文原始线索采编自「arXiv cs.LG」（@Xiaoke Yang, Jin Chen, Yafei Wang, Qi Zhang, Ming Li, Haiwen Wu, Chengliang Yin, Yong Zhang），经 AITOP 多维评分管线结构化提炼。
