Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling

TL;DR

This paper introduces a transformer-augmented MPC framework that enhances trajectory optimization efficiency and convergence, reducing computation time and solver iterations while maintaining high performance in robot control tasks.

Contribution

It proposes embedding transformer-based neural networks into MPC to provide near-optimal initial guesses, improving convergence and reducing computational costs.

Findings

Up to 75% improvement in trajectory generation performance.

Reduced solver iterations by up to 45%.

Achieved 7x faster MPC runtime without performance loss.

Abstract

Model predictive control (MPC) has established itself as the primary methodology for constrained control, enabling general-purpose robot autonomy in diverse real-world scenarios. However, for most problems of interest, MPC relies on the recursive solution of highly non-convex trajectory optimization problems, leading to high computational complexity and strong dependency on initialization. In this work, we present a unified framework to combine the main strengths of optimization-based and learning-based methods for MPC. Our approach entails embedding high-capacity, transformer-based neural network models within the optimization process for trajectory generation, whereby the transformer provides a near-optimal initial guess, or target plan, to a non-convex optimization problem. Our experiments, performed in simulation and the real world onboard a free flyer platform, demonstrate the capabilities of our framework to improve MPC convergence and runtime. Compared to purely optimization-based approaches, results show that our approach can improve trajectory generation performance by up to 75%, reduce the number of solver iterations by up to 45%, and improve overall MPC runtime by 7x without loss in performance.