Gauss-Newton accelerated MPPI Control

2025-12-04

AI Summary

To address the slow convergence and poor scalability of Model Predictive Path Integral (MPPI) control in high-dimensional systems, this paper proposes an acceleration framework integrating Jacobian reconstruction with Generalized Gauss–Newton (GGN) second-order optimization. We are the first to embed GGN into the MPPI iterative pipeline, leveraging analytically reconstructed Jacobians to accurately capture system dynamics nonlinearity and employing second-order curvature information to accelerate policy optimization. The method preserves MPPI’s inherent robustness and parallel sampling capability while significantly improving convergence speed and computational efficiency in high-dimensional settings. Experiments on multi-joint robotic arms and high-degree-of-freedom simulated environments demonstrate that our approach achieves 2.3–5.1× speedup over standard MPPI and improves dimensional scalability by an order of magnitude, establishing a new paradigm for real-time control of complex robotic systems.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Intelligent Robots: State Estimation
• Planning, Routing, and Scheduling: Replanning and Plan Repair

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• User Modeling, Personalization and Recommendation: Practical large-scale studies of user experience
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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 extit{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.

Problem

• Enhances MPPI scalability for high-dimensional control problems
• Improves computational efficiency via Gauss-Newton acceleration
• Maintains robustness and flexibility in model predictive control

Innovation

• Incorporates Jacobian reconstruction technique
• Uses second-order Generalized Gauss-Newton method
• Improves scalability and computational efficiency