Conference proceeding
Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials
Proceedings of the IEEE Conference on Decision & Control, pp.7313-7318
12/09/2025
DOI: 10.1109/CDC57313.2025.11311978
Abstract
In this paper, we propose a Transformer-based framework for approximating solutions to infinite-dimensional optimization problems: calculus of variations problems and optimal control problems. Our approach leverages offline training on data generated by solving a sample of infinite-dimensional optimization problems using composite Bernstein collocation. Once trained, the Transformer efficiently generates near-optimal, feasible trajectories, making it well-suited for real-time applications. In motion planning for autonomous vehicles, for instance, these trajectories can serve to warm-start optimal motion planners or undergo rigorous evaluation to ensure safety. We demonstrate the effectiveness of this method through numerical results on a classical control problem and an online obstacle avoidance task. This data-driven approach offers a promising solution for real-time optimal control of nonlinear, nonconvex systems.
Details
- Title: Subtitle
- Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials
- Creators
- Gage MacLin - University of IowaVenanzio Cichella - University of IowaAndrew Patterson - Langley Research CenterIrene Gregory - Langley Research Center
- Resource Type
- Conference proceeding
- Publication Details
- Proceedings of the IEEE Conference on Decision & Control, pp.7313-7318
- DOI
- 10.1109/CDC57313.2025.11311978
- eISSN
- 2576-2370
- Publisher
- IEEE
- Language
- English
- Date published
- 12/09/2025
- Academic Unit
- Mechanical Engineering
- Record Identifier
- 9985130058802771
Metrics
1 Record Views