Adaptive MPCIntermediate
LLA-MPC on Embedded Hardware: Rapid Adaptive Control with Thousands of Parallel Models
This preprint describes a generalized, learning-free adaptive model-predictive controller that runs thousands of candidate physics models in parallel on embedded hardware. On an F1TENTH car with low-friction tires, it completes high-speed tracking and changing-surface laps where a fixed nominal model crashes within a few laps. The work matters because it shows rapid online system identification and control can run on a small robot computer without pretraining or warm-up data.