Accelerating Sampling-Based Control via Learned Linear Koopman Dynamics
arXiv:2603.05385
The paper proposes a model predictive path integral control method that replaces costly nonlinear dynamics with a learned linear deep Koopman operator, enabling faster trajectory sampling and real‑time control while maintaining performance, demonstrated on pendulum, vehicle navigation, and quadruped robot tasks.
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.