Szczegóły publikacji
Opis bibliograficzny
Constrained optimal formation control for nonlinear multi-agent systems using data-driven adaptive neural networks / Saleh Mobayen, Mai The Vu, Reza Rahmani, Hamid Toshani, Wudhichai Assawinchaichote, Paweł SKRUCH // Engineering Science and Technology, an International Journal [Dokument elektroniczny]. — Czasopismo elektroniczne ; ISSN 2215-0986 . — 2026 — vol. 73 art. no. 102269, s. 1-23. — Wymagania systemowe: Adobe Reader. — Bibliogr. s. 22-23, Abstr. — Publikacja dostępna online od: 2025-12-29
Autorzy (6)
- Mobayen Saleh
- Vu The Mai
- Rahmani Reza
- Toshani Hamid
- Assawinchaichote Wudhichai
- AGHSkruch Paweł
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 165483 |
|---|---|
| Data dodania do BaDAP | 2026-01-26 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.jestch.2025.102269 |
| Rok publikacji | 2026 |
| Typ publikacji | artykuł w czasopiśmie |
| Otwarty dostęp |  |
| Creative Commons | |
| Czasopismo/seria | Engineering Science and Technology, an International Journal |
Abstract
This paper presents a constrained optimal adaptive control strategy for formation control in nonlinear multi-agent systems (MASs) using a data-driven approach. In contrast to traditional methods that require detailed system models, the proposed method employs Locally Linearized Dynamic Models (LLDMs), in which key parameters as Pseudo-Partial Derivatives (PPDs) are estimated adaptively from input–output data. This removes the need for explicit mathematical modeling and broadens the method’s applicability to uncertain systems. To address actuator limitations and reduce control effort, a performance criterion incorporating control constraints is defined, and the problem is reformulated as a Constrained Quadratic Program (CQP) with control increments as optimization variables. A Projection Recurrent Neural Network (PRNN) is developed to solve this CQP in real time, which ensures convergence of the numerical optimizer and guarantees closed-loop stability using Lyapunov analysis and singular value approach. The proposed algorithm achieves robust, model-free formation control, explicitly manages input constraints, and enables fast convergence. Simulation results show that this approach outperforms existing data-driven methods under uncertainty, which demonstrates its potential for applications in multi-agent system applications.
