Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhou, Jingyuan, Wu, Haoze, Yang, Kaidi
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2601.20324
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910003279953920
author Zhou, Jingyuan
Wu, Haoze
Yang, Kaidi
author_facet Zhou, Jingyuan
Wu, Haoze
Yang, Kaidi
contents Providing formal guarantees for neural network-based controllers in large-scale interconnected systems remains a fundamental challenge. In particular, using neural certificates to capture cooperative interactions and verifying these certificates at scale is crucial for the safe deployment of such controllers. However, existing approaches fall short on both fronts. To address these limitations, we propose neural cooperative reach-while-avoid certificates with Dynamic-Localized Vector Control Lyapunov and Barrier Functions, which capture cooperative dynamics through state-dependent neighborhood structures and provide decentralized certificates for global exponential stability and safety. Based on the certificates, we further develop a scalable training and verification framework that jointly synthesizes controllers and neural certificates via a constrained optimization objective, and leverages a sufficient condition to ensure formal guarantees considering modeling error. To improve scalability, we introduce a structural reuse mechanism to transfer controllers and certificates between substructure-isomorphic systems. The proposed methodology is validated with extensive experiments on multi-robot coordination and vehicle platoons. Results demonstrate that our framework ensures certified cooperative reach-while-avoid while maintaining strong control performance.
format Preprint
id arxiv_https___arxiv_org_abs_2601_20324
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Cooperative Reach-While-Avoid Certificates for Interconnected Systems
Zhou, Jingyuan
Wu, Haoze
Yang, Kaidi
Systems and Control
Providing formal guarantees for neural network-based controllers in large-scale interconnected systems remains a fundamental challenge. In particular, using neural certificates to capture cooperative interactions and verifying these certificates at scale is crucial for the safe deployment of such controllers. However, existing approaches fall short on both fronts. To address these limitations, we propose neural cooperative reach-while-avoid certificates with Dynamic-Localized Vector Control Lyapunov and Barrier Functions, which capture cooperative dynamics through state-dependent neighborhood structures and provide decentralized certificates for global exponential stability and safety. Based on the certificates, we further develop a scalable training and verification framework that jointly synthesizes controllers and neural certificates via a constrained optimization objective, and leverages a sufficient condition to ensure formal guarantees considering modeling error. To improve scalability, we introduce a structural reuse mechanism to transfer controllers and certificates between substructure-isomorphic systems. The proposed methodology is validated with extensive experiments on multi-robot coordination and vehicle platoons. Results demonstrate that our framework ensures certified cooperative reach-while-avoid while maintaining strong control performance.
title Neural Cooperative Reach-While-Avoid Certificates for Interconnected Systems
topic Systems and Control
url https://arxiv.org/abs/2601.20324