Gauss-Newton accelerated MPPI Control

TL;DR

This paper introduces Gauss-Newton accelerated MPPI, an improved control method that enhances scalability and efficiency for high-dimensional optimal control problems by integrating second-order optimization techniques.

Contribution

It presents a novel Gauss-Newton accelerated MPPI method that combines Jacobian reconstruction and second-order optimization to improve performance in high-dimensional settings.

Findings

Significant scalability improvements demonstrated.

Enhanced computational efficiency over classical MPPI.

Preservation of MPPI's robustness and flexibility.

Abstract

Model Predictive Path Integral (MPPI) control is a sampling-based optimization method that has recently attracted attention, particularly in the robotics and reinforcement learning communities. MPPI has been widely applied as a GPU-accelerated random search method to deterministic direct single-shooting optimal control problems arising in model predictive control (MPC) formulations. MPPI offers several key advantages, including flexibility, robustness, ease of implementation, and inherent parallelizability. However, its performance can deteriorate in high-dimensional settings since the optimal control problem is solved via Monte Carlo sampling. To address this limitation, this paper proposes an enhanced MPPI method that incorporates a Jacobian reconstruction technique and the second-order Generalized Gauss-Newton method. This novel approach is called \textit{Gauss-Newton accelerated MPPI}. The numerical results show that the Gauss-Newton accelerated MPPI approach substantially improves MPPI scalability and computational efficiency while preserving the key benefits of the classical MPPI framework, making it a promising approach even for high-dimensional problems.