LLA-MPC on Embedded Hardware: Rapid Adaptive Control with Thousands of Parallel Models

2026-10-02

AI Summary

This study addresses the challenge that fixed models in embedded real-time control struggle to adapt to dynamic tire parameter variations and noise disturbances. We propose LLA-MPC, a learning-free framework that pioneers the integration of massively parallel computation into resource-constrained embedded systems. By evaluating thousands of candidate models online in parallel, it enables real-time tire parameter identification and supports modular dynamics modeling, achieving rapid environmental adaptation without offline training. Experimental validation on the F1TENTH platform demonstrates that the proposed framework successfully executes high-speed tracking tasks under low-friction and varying road conditions, significantly outperforming conventional approaches based on fixed nominal models.

Abstract

We present a generalized implementation of Look-Back and Look-Ahead Adaptive Model Predictive Control (LLA-MPC), a learning-free framework for real-time, rapid adaptive system identification and control. The original formulation was demonstrated only in simulation, for autonomous racing with a fixed model structure. Our implementation has modular dynamics and integrators, and we validate it on the F1TENTH platform under constrained computation and noisy state estimation. The system identifies tire parameters online by evaluating thousands of candidate models in real time on an embedded computer. Experiments with low-friction tires across changing surfaces show that LLA-MPC completes high-speed tracking tasks where a fixed nominal model fails. Code, videos, and our related work are available at: https://lla-control.github.io.

Problem

• Adaptive Model Predictive Control
• Embedded Hardware
• Online System Identification
• Real-time Control
• Constrained Computation

Innovation

• Adaptive Model Predictive Control
• Embedded Hardware
• Online System Identification
• Parallel Models
• F1TENTH