Koopman Operator Framework for Modeling and Control of Off-Road Vehicle on Deformable Terrain

TL;DR

This paper introduces a hybrid physics-informed and data-driven Koopman operator framework for predictive control of off-road vehicles on deformable terrain, enabling efficient and robust control strategies.

Contribution

It develops a method to construct and update Koopman linear models from simulation and real data for off-road vehicle control on deformable terrain.

Findings

Koopman models accurately predict vehicle dynamics on deformable terrain.

The approach enables stable closed-loop control of aggressive maneuvers.

Models can be updated seamlessly with new data from physical systems.

Abstract

This work presents a hybrid physics-informed and data-driven modeling framework for predictive control of autonomous off-road vehicles operating on deformable terrain. Traditional high-fidelity terramechanics models are often too computationally demanding to be directly used in control design. Modern Koopman operator methods can be used to represent the complex terramechanics and vehicle dynamics in a linear form. We develop a framework whereby a Koopman linear system can be constructed using data from simulations of a vehicle moving on deformable terrain. For vehicle simulations, the deformable-terrain terramechanics are modeled using Bekker-Wong theory, and the vehicle is represented as a simplified five-degree-of-freedom (5-DOF) system. The Koopman operators are identified from large simulation datasets for sandy loam and clay using a recursive subspace identification method, where Grassmannian distance is used to prioritize informative data segments during training. The advantage of this approach is that the Koopman operator learned from simulations can be updated with data from the physical system in a seamless manner, making this a hybrid physics-informed and data-driven approach. Prediction results demonstrate stable short-horizon accuracy and robustness under mild terrain-height variations. When embedded in a constrained MPC, the learned predictor enables stable closed-loop tracking of aggressive maneuvers while satisfying steering and torque limits.