Lyapunov-based Adaptive Transformer (LyAT) for Control of Stochastic Nonlinear Systems

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Akbari, Saiedeh, Shen, Xuehui, Xue, Wenqian, Insinger, Jordan C., Dixon, Warren E.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911325423140864
author Akbari, Saiedeh
Shen, Xuehui
Xue, Wenqian
Insinger, Jordan C.
Dixon, Warren E.
author_facet Akbari, Saiedeh
Shen, Xuehui
Xue, Wenqian
Insinger, Jordan C.
Dixon, Warren E.
contents This paper presents a novel Lyapunov-based Adaptive Transformer (LyAT) controller for stochastic nonlinear systems. While transformers have shown promise in various control applications due to sequential modeling through self-attention mechanisms, they have not been used within adaptive control architectures that provide stability guarantees. Existing transformer-based approaches for control rely on offline training with fixed weights, resulting in open-loop implementations that lack real-time adaptation capabilities and stability assurances. To address these limitations, a continuous LyAT controller is developed that adaptively estimates drift and diffusion uncertainties in stochastic dynamical systems without requiring offline pre-training. A key innovation is the analytically derived adaptation law constructed from a Lyapunov-based stability analysis, which enables real-time weight updates while guaranteeing probabilistic uniform ultimate boundedness of tracking and parameter estimation errors. Experimental validation on a quadrotor demonstrates the performance of the developed controller.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15996
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lyapunov-based Adaptive Transformer (LyAT) for Control of Stochastic Nonlinear Systems
Akbari, Saiedeh
Shen, Xuehui
Xue, Wenqian
Insinger, Jordan C.
Dixon, Warren E.
Systems and Control
This paper presents a novel Lyapunov-based Adaptive Transformer (LyAT) controller for stochastic nonlinear systems. While transformers have shown promise in various control applications due to sequential modeling through self-attention mechanisms, they have not been used within adaptive control architectures that provide stability guarantees. Existing transformer-based approaches for control rely on offline training with fixed weights, resulting in open-loop implementations that lack real-time adaptation capabilities and stability assurances. To address these limitations, a continuous LyAT controller is developed that adaptively estimates drift and diffusion uncertainties in stochastic dynamical systems without requiring offline pre-training. A key innovation is the analytically derived adaptation law constructed from a Lyapunov-based stability analysis, which enables real-time weight updates while guaranteeing probabilistic uniform ultimate boundedness of tracking and parameter estimation errors. Experimental validation on a quadrotor demonstrates the performance of the developed controller.
title Lyapunov-based Adaptive Transformer (LyAT) for Control of Stochastic Nonlinear Systems
topic Systems and Control
url https://arxiv.org/abs/2512.15996