Differentiable Weights-Varying Nonlinear MPC via Gradient-Based Policy Learning: An Autonomous Vehicle Guidance Example

Abstract

Tuning Model Predictive Control (MPC) cost weights for multiple, competing objectives is labor-intensive. Derivative-free automated methods, such as Bayesian Optimization, reduce manual effort but remain slow, while Differentiable MPC (Diff-MPC) exploits solver sensitivities for faster gradient-based tuning. However, existing Diff-MPC approaches learn a single global weight set, which may be suboptimal as operating conditions change. Conversely, black-box Reinforcement Learning Weights-Varying MPC (RL-WMPC) requires long training times and a lot of data. In this work, we introduce gradient-based policy learning for Differentiable Weights-Varying MPC (Diff-WMPC). By backpropagating solver-in-the-loop sensitivities through a lightweight policy that maps look-ahead observations to MPC weights, our Diff-WMPC yields rapid, sample-efficient adaptation at runtime. Extensive simulation on a full-scale racecar model demonstrates that Diff-WMPC outperforms state-of-the-art static-weight baselines and is competitive with weights-varying algorithms, while reducing training time from over an hour to under two minutes relative to RL-WMPC. The learned policy transfers zero-shot to unseen conditions and, with quick online fine-tuning, reaches environment-specific performance. Project Website: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://diffmpc.com</uri>