Transformer-based Model Predictive Control: Trajectory Optimization via Sequence Modeling
This addresses efficiency and convergence issues in MPC for robot autonomy, offering a hybrid optimization-learning approach that is incremental but provides strong specific gains.
The paper tackles the high computational complexity and initialization dependency of model predictive control (MPC) by embedding transformer-based neural networks to provide near-optimal initial guesses for trajectory optimization, resulting in up to 75% performance improvement, 45% reduction in solver iterations, and 7x runtime speedup without performance loss.
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.