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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Alentev, Igor, Kozlov, Lev, Domrachev, Ivan, Nedelchev, Simeon, Ryu, Jee-Hwan
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908362917019648
author Alentev, Igor
Kozlov, Lev
Domrachev, Ivan
Nedelchev, Simeon
Ryu, Jee-Hwan
author_facet Alentev, Igor
Kozlov, Lev
Domrachev, Ivan
Nedelchev, Simeon
Ryu, Jee-Hwan
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2505_05507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VIMPPI: Enhancing Model Predictive Path Integral Control with Variational Integration for Underactuated Systems
Alentev, Igor
Kozlov, Lev
Domrachev, Ivan
Nedelchev, Simeon
Ryu, Jee-Hwan
Systems and Control
Robotics
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
title VIMPPI: Enhancing Model Predictive Path Integral Control with Variational Integration for Underactuated Systems
topic Systems and Control
Robotics
url https://arxiv.org/abs/2505.05507