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

TL;DR

VIMPPI introduces a variational integration-enhanced MPPI control method for underactuated systems, achieving longer planning horizons and higher operational speeds, significantly improving performance in complex control tasks.

Contribution

The paper develops VIMPPI, a novel control framework that integrates variational techniques into MPPI, enabling efficient, high-speed control of underactuated systems.

Findings

Operates at 500-700 Hz with control interpolation

Outperforms baseline and alternative MPPI methods

Enables longer planning horizons without extra computational cost

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