mlsanityData to 14 Oct 2026

Stability-Aware Imitation Learning from Model Predictive Control for Autonomous Vehicle Lateral Control: Exact Q-Loss and a Novel Training Procedure

arXiv 2609.23506 ↗First posted 20 Sep 2026eess.SY cs.SYcited by 0

On the map: End-to-end autonomous driving → Imitation-learning end-to-end planners also fits: Reinforcement learning for driving

also in 1 more
Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Imitation-learning end-to-end planners, one of 9 directions in End-to-end autonomous driving. Builds on 10 of its 18 references that are in the map. First posted on arXiv 20 Sep 2026.

Builds on

10 of 18 references.

References · 10

  1. 2016Generative Adversarial Imitation Learningcited by 1,597
  2. 2017OptNet: Differentiable Optimization as a Layer in Neural Networkscited by 599
  3. 2019Differentiable Convex Optimization Layerscited by 465
  4. 2018Lipschitz regularity of deep neural networks: analysis and efficient estimationcited by 415
  5. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 293
  6. 2018Differentiable MPC for End-to-end Planning and Controlcited by 189
  7. 2014Analysis and Design of Optimization Algorithms via Integral Quadratic Constraintscited by 105
  8. 2018Efficient representation and approximation of model predictive control laws via deep learningcited by 58
  9. 2018Learning an Approximate Model Predictive Controller with Guaranteescited by 57
  10. 2017DropoutDAgger: A Bayesian Approach to Safe Imitation Learningcited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2022MPC-based Imitation Learning for Safe and Human-like Autonomous Driving
  2. 2022Evaluation of MPC-based Imitation Learning for Human-like Autonomous Driving
  3. 2019Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
  4. 2026A Hybrid End-to-End and Modular Control Architecture Toward Safe Vehicle Lateral Control: Combining Soft Actor-Critic with Model Predictive Control
  5. 2023Imitation Learning from Nonlinear MPC via the Exact Q-Loss and its Gauss-Newton Approximation
  6. 2018Safe end-to-end imitation learning for model predictive control
  7. 2026Dynamics Distillation for Efficient and Transferable Control Learning
  8. 2025Bridging the Sim-to-real Gap: A Control Framework for Imitation Learning of Model Predictive Control