Skip to content

VIMPPI: Enhancing Model Predictive Path Integral Control with Variational Integration for Underactuated Systems

Authors: Igor Alentev, Lev Kozlov, Ivan Domrachev, Simeon Nedelchev, Jee-Hwan Ryu

Published: 2025 (Preprint)

Source: arXiv

Algorithm: VIMPPI

arXiv: 2505.05507

Summary

Enhances MPPI with variational integration (VI) to accurately simulate the system evolution inside an MPPI over long planning horizons.

Abstract

This paper presents VIMPPI, a novel control approach for underactuated double pendulum systems developed for the AI Olympics competition. We enhance the Model Predictive Path Integral framework by incorporating variational integration techniques, enabling longer planning horizons without additional computational cost. Operating at 500-700 Hz with control interpolation and disturbance detection mechanisms, VIMPPI substantially outperforms both baseline methods and alternative MPPI implementations.

Primary

Paper arxiv.org

Standard

arXiv Abstract 2505.05507 arXiv PDF 2505.05507 arXiv HTML 2505.05507

Tags

  • MPPI

  • Trajectory optimization

  • Sampling-based control

  • Variational integration

  • Underactuated systems