稳定性感知的模型预测控制模仿学习用于自动驾驶车辆横向控制：精确Q损失与新颖训练流程
Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure
- Ho Chi Minh City University of Technology (HCMUT), Vietnam National University Ho Chi Minh City (VNU-HCM)（胡志明市理工大学（HCMUT），越南国立大学胡志明市分校）
- Hanoi University of Science and Technology (HUST)（河内科技大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本文提出一种稳定性感知的模仿学习框架，通过精确Q损失和基于Lyapunov-IQC的认证裕度训练神经控制器逼近MPC策略，并在自动驾驶车辆横向控制实验中验证了闭环性能。
AI中文摘要：
本文开发了一个经过认证的模仿学习框架，用于用前馈神经控制器逼近模型预测控制（MPC）策略，并在自动驾驶车辆横向控制上进行了验证。通过在专家MPC问题中固定学习者的第一个转向动作并重新优化剩余时域，构建了精确的有限时域Q损失，从而衡量其下游最优控制后果，而不仅仅是逐点动作不匹配。神经策略被表示为线性分式变换（LFT）互连，激活非线性由扇形积分二次约束（IQCs）描述。结合二次Lyapunov条件，该表示产生基于Lyapunov-IQC矩阵最大特征值的可微认证裕度。训练期间通过对数障碍强制执行该裕度，而经过认证的数据聚合（DAgger）和安全投影将数据聚合回滚保持在认证策略集内。在带有AprilTag定位和实时转向的CAD参考自动驾驶车辆平台上的实验证明了所得到的闭环性能。
英文摘要：
This paper develops a certified imitation-learning framework for approximating model predictive control (MPC) policies with feedforward neural controllers and validates it on autonomous-vehicle lateral control. An exact finite-horizon Q-loss is constructed by fixing the learner's first steering action in the expert MPC problem and re-optimizing the remaining horizon, thereby measuring its downstream optimal-control consequence rather than only pointwise action mismatch. The neural policy is represented as a linear fractional transformation (LFT) interconnection with activation nonlinearities described by sector integral quadratic constraints (IQCs). Combined with a quadratic Lyapunov condition, this representation yields a differentiable certification margin based on the largest eigenvalue of the Lyapunov-IQC matrix. The margin is enforced during training through a logarithmic barrier, while certified Dataset Aggregation (DAgger) and safe projection keep data-aggregation rollouts within the certified policy set. Experiments on a CAD-referenced autonomous-vehicle platform with AprilTag localization and real-time steering demonstrate the resulting closed-loop performance.
