Transformer-based explicit model predictive control with variable prediction horizon

Traditional online Model Predictive Control (MPC) methods often suffer from excessive computational complexity, limiting their practical deployment. Explicit MPC mitigates online computational load by pre-computing control policies offline, however, existing explicit MPC methods typically rely on simplified system dynamics and cost functions, restricting their accuracy for complex systems. This paper proposes a novel Transformer-based explicit MPC algorithm (TransMPC) capable of generating highly accurate control sequences in real-time for complex dynamic systems. The Transformer is a deep learning architecture utilizing self-attention mechanisms to process sequential data. Specifically, we formulate the MPC policy as an encoder-only Transformer leveraging bidirectional self-attention, enabling simultaneous inference of entire control sequences in a single forward pass. This design inherently accommodates variable prediction horizons while ensuring low inference latency. Furthermore, we introduce a direct policy optimization framework that alternates between sampling and learning phases. Unlike imitation-based approaches dependent on precomputed optimal trajectories, TransMPC directly optimizes the true finite-horizon cost via automatic differentiation. Random horizon sampling combined with a replay buffer provides independent and identically distributed (i. i. d.) training samples, ensuring robust generalization across varying states and horizon lengths. Extensive simulations and real-world multi-platform experiments demonstrate that TransMPC achieves up to 81. 97%–516. 74% faster inference than recurrent-based methods, while maintaining high accuracy in both tracking and manipulation tasks. Specifically, in the mobile robot trajectory tracking task, TransMPC achieves lateral tracking errors as low as 0. 008 m, along with millimeter-level positioning and sub-degree orientation accuracy on a 7-degrees of freedom drill arm.

Authors

• Sichao Wu
• Jiang Wu Shanghai Artificial Intelligence Laboratory
• Xingyu Cao
• Fawang Zhang
• Guangyuan Yu
• Junjie Zhao
• Yue Qu
• Fei Ma Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)
• Jingliang Duan University of Science and Technology Beijing

Keywords

• Explicit model predictive control
• Policy optimization
• Finite-horizon control
• Policy approximation
• Variable prediction horizon