FastDOC uses Gauss-Newton Hessian approximation to create block-sparse positive semidefinite matrices in the differential KKT system, enabling a factor-of-two reduction in factorization complexity and up to 180% empirical speedup over prior auxiliary-system methods for differentiable NMPC.
Differentiable model predictive control on the gpu
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
representative citing papers
GPU-SLS computes safe robust nonlinear MPC policies online in ~20 ms for up to 75D systems by reachability-constrained system level synthesis accelerated via custom GPU QP solvers.
AD-MPCC integrates differentiable MPCC, online Pacejka parameter estimation via moving-horizon methods, and a supervised ML model to adapt objective weights, yielding safer and faster simulated laps on varying surfaces.
CA-AC-MPC uses CUDA to accelerate the differentiable MPC layer in actor-critic control, delivering state-of-the-art drone racing performance with substantially lower training and inference latency.
citing papers explorer
-
Safe Large-Scale Robust Nonlinear MPC in Milliseconds via Reachability-Constrained System Level Synthesis on the GPU
GPU-SLS computes safe robust nonlinear MPC policies online in ~20 ms for up to 75D systems by reachability-constrained system level synthesis accelerated via custom GPU QP solvers.
-
AD-MPCC: Adaptive Differentiable Model Predictive Contouring Control for Autonomous Racing
AD-MPCC integrates differentiable MPCC, online Pacejka parameter estimation via moving-horizon methods, and a supervised ML model to adapt objective weights, yielding safer and faster simulated laps on varying surfaces.
-
CA-AC-MPC: CUDA-Accelerated Actor-Critic Model Predictive Control
CA-AC-MPC uses CUDA to accelerate the differentiable MPC layer in actor-critic control, delivering state-of-the-art drone racing performance with substantially lower training and inference latency.