Accelerating Sampling-Based Control via Learned Linear Koopman Dynamics

TL;DR

This paper introduces MPPI-DK, a control method that uses learned linear Koopman dynamics to accelerate sampling-based control, achieving near-true performance with reduced computation for complex nonlinear systems.

Contribution

The paper proposes a novel MPPI control framework utilizing a learned linear Koopman operator to replace nonlinear dynamics, enabling faster trajectory sampling and real-time control without analytical models.

Findings

MPPI-DK achieves control performance close to traditional MPPI.

Significant reduction in computational cost for control tasks.

Successful validation on robotic hardware with real-time capabilities.

Abstract

This paper presents an efficient model predictive path integral (MPPI) control framework for systems with complex nonlinear dynamics. To improve the computational efficiency of classic MPPI while preserving control performance, we replace the nonlinear dynamics used for trajectory propagation with a learned linear deep Koopman operator (DKO) model, enabling faster rollout and more efficient trajectory sampling. The DKO dynamics are learned directly from interaction data, eliminating the need for analytical system models. The resulting controller, termed MPPI-DK, is evaluated in simulation on pendulum balancing and surface vehicle navigation tasks, and validated on hardware through reference-tracking experiments on a quadruped robot. Experimental results demonstrate that MPPI-DK achieves control performance close to MPPI with true dynamics while substantially reducing computational cost, enabling efficient real-time control on robotic platforms.