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

2025/05/07 by Igor Alentev, Л. А. Козлов, Alentev, Igor +7
Engineering · #Adaptive Control of Nonlinear Systems #Advanced Control Systems Optimization #Control and Dynamics of Mobile Robots #FOS: Computer and information sciences #FOS: Electrical engineering #Robotics (cs.RO) #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.05507

openalex publication_date 2025/05/07 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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

Citations

• Reinforcement Learning for Robust Athletic Intelligence: Lessons from the 2nd 'AI Olympics with RealAIGym' Competition
• Average-Reward Maximum Entropy Reinforcement Learning for Underactuated Double Pendulum Tasks
• Learning control of underactuated double pendulum with Model-Based Reinforcement Learning
• AI Olympics challenge with Evolutionary Soft Actor Critic
• Sampling-Based Motion Planning: A Comparative Review

Related

• Real-Time Model Predictive Control for the Swing-Up Problem of an Underactuated Double Pendulum
• Learning control of underactuated double pendulum with Model-Based Reinforcement Learning
• LP-MPPI: Low-Pass Filtering for Efficient Model Predictive Path Integral Control
• Model Predictive Optimized Path Integral Strategies
• Feedback-MPPI: Fast Sampling-Based MPC via Rollout Differentiation -- Adios low-level controllers