Nonplanar Model Predictive Control for Autonomous Vehicles with Recursive Sparse Gaussian Process Dynamics

TL;DR

This paper introduces a nonplanar MPC framework for autonomous vehicles that uses recursive sparse Gaussian Processes to adapt to complex 3D terrains in real-time, improving tracking accuracy.

Contribution

It presents a geometry-aware residual GP modeling approach combined with recursive sparse GPs for real-time terrain adaptation in nonplanar MPC for autonomous vehicles.

Findings

High tracking accuracy on challenging 3D surfaces

Effective real-time adaptation to terrain variations

Validated in a custom simulation environment

Abstract

This paper proposes a nonplanar model predictive control (MPC) framework for autonomous vehicles operating on nonplanar terrain. To approximate complex vehicle dynamics in such environments, we develop a geometry-aware modeling approach that learns a residual Gaussian Process (GP). By utilizing a recursive sparse GP, the framework enables real-time adaptation to varying terrain geometry. The effectiveness of the learned model is demonstrated in a reference-tracking task using a Model Predictive Path Integral (MPPI) controller. Validation within a custom Isaac Sim environment confirms the framework's capability to maintain high tracking accuracy on challenging 3D surfaces.