Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: MacLin, Gage, Cichella, Venanzio, Patterson, Andrew, Gregory, Irene
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909913674940416
author MacLin, Gage
Cichella, Venanzio
Patterson, Andrew
Gregory, Irene
author_facet MacLin, Gage
Cichella, Venanzio
Patterson, Andrew
Gregory, Irene
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_15588
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials
MacLin, Gage
Cichella, Venanzio
Patterson, Andrew
Gregory, Irene
Optimization and Control
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.
title Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials
topic Optimization and Control
url https://arxiv.org/abs/2511.15588