Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909831004160000 |
|---|---|
| author | Hedesh, Hamidreza Montazeri Siami, Milad |
| author_facet | Hedesh, Hamidreza Montazeri Siami, Milad |
| contents | We present a risk-aware safety certification method for autonomous, learning enabled control systems. Focusing on two realistic risks, state/input delays and interval matrix uncertainty, we model the neural network (NN) controller with local sector bounds and exploit positivity structure to derive linear, delay-independent certificates that guarantee local exponential stability across admissible uncertainties. To benchmark performance, we adopt and implement a state-of-the-art IQC NN verification pipeline. On representative cases, our positivity-based tests run orders of magnitude faster than SDP-based IQC while certifying regimes the latter cannot-providing scalable safety guarantees that complement risk-aware control. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06661 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy Hedesh, Hamidreza Montazeri Siami, Milad Systems and Control Artificial Intelligence 93D09, 93D20, 93C10, 68T07 I.2.0; I.2.3; I.2.8; B.1.3; G.2; F.3 We present a risk-aware safety certification method for autonomous, learning enabled control systems. Focusing on two realistic risks, state/input delays and interval matrix uncertainty, we model the neural network (NN) controller with local sector bounds and exploit positivity structure to derive linear, delay-independent certificates that guarantee local exponential stability across admissible uncertainties. To benchmark performance, we adopt and implement a state-of-the-art IQC NN verification pipeline. On representative cases, our positivity-based tests run orders of magnitude faster than SDP-based IQC while certifying regimes the latter cannot-providing scalable safety guarantees that complement risk-aware control. |
| title | Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy |
| topic | Systems and Control Artificial Intelligence 93D09, 93D20, 93C10, 68T07 I.2.0; I.2.3; I.2.8; B.1.3; G.2; F.3 |
| url | https://arxiv.org/abs/2510.06661 |