{"ID":2872866,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.07381","arxiv_id":"2509.07381","title":"TransMPC: Transformer-based Explicit MPC with Variable Prediction Horizon","abstract":"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 TransMPC, a novel Transformer-based explicit MPC algorithm capable of generating highly accurate control sequences in real-time for complex dynamic systems. 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 vehicle control experiments validate the effectiveness of TransMPC in terms of solution accuracy, adaptability to varying horizons, and computational efficiency.","short_abstract":"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 dyna...","url_abs":"https://arxiv.org/abs/2509.07381","url_pdf":"https://arxiv.org/pdf/2509.07381v1","authors":"[\"Sichao Wu\",\"Jiang Wu\",\"Xingyu Cao\",\"Fawang Zhang\",\"Guangyuan Yu\",\"Junjie Zhao\",\"Yue Qu\",\"Fei Ma\",\"Jingliang Duan\"]","published":"2025-09-09T04:14:42Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Transformer\"]","has_code":false}