Robust Path Tracking for Vehicles via Continuous-Time Residual Learning: An ICODE-MPPI Approach

TL;DR

This paper introduces ICODE-MPPI, a novel control framework that enhances model predictive path tracking by learning residual dynamics with continuous-time neural ODEs, resulting in improved robustness and smoother control.

Contribution

The paper presents ICODE-MPPI, integrating continuous-time neural ODEs into MPPI to better handle unmodeled dynamics and improve robustness in vehicle path tracking.

Findings

Achieves up to 69% reduction in cross-tracking error under disturbances.

Significantly suppresses control chattering for smoother steering.

Demonstrates superior robustness compared to standard MPPI.

Abstract

Model Predictive Path Integral (MPPI) control is a powerful sampling-based strategy for nonlinear autonomous systems. However, its performance is often bottlenecked by the fidelity of nominal dynamics. We propose ICODE-MPPI, a robust framework that leverages Input Concomitant Neural Ordinary Differential Equations (ICODEs) to learn and compensate for unmodeled residual dynamics. Unlike discrete-time learners, ICODEs maintain physical consistency and temporal continuity during the MPPI prediction horizon. High-fidelity simulations on complex trajectories demonstrate that ICODE-MPPI achieves up to a 69\% reduction in cross-tracking error under persistent disturbances compared to standard MPPI control. Furthermore, our analysis confirms that ICODE-MPPI significantly suppresses control chattering, yielding smoother steering commands and superior robust performance.