Transformer-Based Model Predictive Path Integral Control
Preprint
Abstract
This paper presents a novel approach to improve the Model Predictive Path Integral (MPPI) control by using a transformer to initialize the mean control sequence. Traditional MPPI methods often struggle with sample efficiency and computational costs due to suboptimal initial rollouts. We propose TransformerMPPI, which uses a transformer trained on historical control data to generate informed initial mean control sequences. TransformerMPPI combines the strengths of the attention mechanism in transformers and sampling-based control, leading to improved computational performance and sample efficiency. The ability of the transformer to capture long-horizon patterns in optimal control sequences allows TransformerMPPI to start from a more informed control sequence, reducing the number of samples required, and accelerating convergence to optimal control sequence. We evaluate our method on various control tasks, including avoidance of collisions in a 2D environment and autonomous racing in the presence of static and dynamic obstacles. Numerical simulations demonstrate that TransformerMPPI consistently outperforms traditional MPPI algorithms in terms of overall average cost, sample efficiency, and computational speed in the presence of static and dynamic obstacles.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Model Predictive Path Integral Control for Agile Unmanned Aerial Vehicles2024
- Multi-Modal MPPI and Active Inference for Reactive Task and Motion PlanningIEEE Robotics and Automation Letters, 2024
- Safety Barrier Certificates for Path Integral Control: Safety-Critical Control of QuadrotorsIEEE Robotics and Automation Letters, 2023
- Real-Time Perception-Limited Motion Planning Using Sampling-Based MPCIEEE Transactions on Industrial Electronics, 2022
- Constrained stochastic optimal control with learned importance sampling: A path integral approachThe International Journal of Robotics Research, 2021
- Model-Based Generalization Under Parameter Uncertainty Using Path Integral ControlIEEE Robotics and Automation Letters, 2020
- Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous DrivingIEEE Transactions on Robotics, 2018
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- Spacecraft attitude control using explicit model predictive controlAutomatica, 2005
- Review on model predictive control: an engineering perspective