Brian Plancher

Tue, 13 Oct 2026 00:00:00 +0000

Efficient Learning of Differentiable MPC Policies on the GPU via Smoothed ADMM and First-Order Reinforcement Learning

Tue, 13 Oct 2026 00:00:00 +0000

We first introduce SmoothedTurboMPC, a GPU-parallel differentiable MPC solver combining sequential quadratic programming (SQP) with a log-barrier-smoothed alternating direction method of multipliers (ADMM) inner solver. Its design enables smooth gradients, exact sensitivities at convergence, and efficient execution on GPUs. Second, to efficiently train MPC policies, we pair our solver with first-order reinforcement learning (FORL) using Short-Horizon Actor-Critic (SHAC), which reuses rollout MPC solutions instead of repeatedly re-evaluating them. Comparisons with state of the art solvers show that the approach achieves up to 4.4× higher end-to-end training throughput. On a vehicle racing task, our method achieves higher returns than MPC PPO with a 46× speedup, training on 3.3 million transitions in only 7 minutes. Finally, we use the framework to train a more reliable MPC racing policy via RL with domain randomization, and validate it on a full-scale race car. We integrate our advances into the open-source TurboMPC solver.

TurboMPC: Fast, Scalable, and Differentiable Model Predictive Control on the GPU

Tue, 23 Jun 2026 00:00:00 +0000

We present TurboMPC, a differentiable MPC solver that runs entirely on the GPU and supports state and control inequality constraints, implicit integrators, cross-time-coupled costs, and slack variables. TurboMPC combines sequential quadratic programming (SQP), an alternating direction method of multipliers (ADMM) inner solver, implicit differentiation, and a co-designed JAX-CUDA implementation for efficiency and ease of use. In simulation, we achieve up to 15x and 58x speedups over state-of-the-art CPU and GPU differentiable solvers, respectively. We deploy TurboMPC on a full-scale car for minimum-time racing and scale to planning horizons of over 8000 knot points while maintaining control of the vehicle. We open-source TurboMPC at https://github.com/ToyotaResearchInstitute/turbompc