Track trials, findings, and clinical evidence as it lands.
Search papers, labs, and topics across Lattice.
This paper introduces a temporally decomposed, scalable learned iterative solver for nonlinear MPC (NMPC) that decouples network size from the prediction horizon, addressing a key limitation of prior monolithic learned solvers. By learning to predict primal-dual steps via self-supervised training and incorporating a closed-loop resampling strategy, the solver achieves horizon-independent network scaling without sacrificing training loss or iteration count. Empirical results on a CSTR cascade benchmark demonstrate significant speedups over IPOPT and comparable closed-loop performance with no constraint violations.
Horizon-independent learned NMPC solvers now scale to larger problems, achieving four-fold speedups over IPOPT with perfect constraint satisfaction.
Nonlinear model predictive control (NMPC) can be applied to large nonlinear systems with complex objectives while enforcing constraints, but the cost of solving the underlying optimization problems limits real-time application for systems with fast dynamics or many states. Neural networks can reduce this online cost by approximating the control law, but may violate constraints and typically require many precomputed optimizer solutions for training. The learning-based iterative solver for constrained optimization (LISCO) instead learns to predict primal-dual steps toward satisfaction of the Karush-Kuhn-Tucker (KKT) conditions through self-supervised training without precomputed solutions, but its dense, monolithic architecture grows with the prediction horizon. We remove this horizon dependence by exploiting the temporal structure of the problem in the solver architecture, which makes the network size independent of the horizon while leaving the training loss and the solver iteration unchanged. A closed-loop resampling strategy further aligns the training distribution with closed-loop operation at no additional sampling cost. On an economic NMPC benchmark of a CSTR cascade, the proposed solver scales to larger problems than monolithic LISCO and achieves median speedups of up to a factor of four over IPOPT. In closed loop, it achieves comparable control performance to IPOPT with no observed constraint violations.