PAC One-Step Safety Certification for Black-Box Discrete-Time Stochastic Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918337507753984 |
|---|---|
| author | Wu, Taoran Wagner, Dominik Pan, Jingduo Ong, Luke Easwaran, Arvind Xue, Bai |
| author_facet | Wu, Taoran Wagner, Dominik Pan, Jingduo Ong, Luke Easwaran, Arvind Xue, Bai |
| contents | This paper investigates the problem of safety certification for black-box discrete-time stochastic systems, where both the system dynamics and disturbance distributions are unknown, and only sampled data are available. Under such limited information, ensuring robust or classical quantitative safety over finite or infinite horizons is generally infeasible. To address this challenge, we propose a data-driven framework that provides theoretical one-step safety guarantees in the Probably Approximately Correct (PAC) sense. This one-step guarantee can be applied recursively at each time step, thereby yielding step-by-step safety assurances over extended horizons. Our approach formulates barrier certificate conditions based solely on sampled data and establishes PAC safety guarantees by leveraging the VC dimension, scenario approaches, Markov's inequality, and Hoeffding's inequality. Two sampling procedures are proposed, and three methods are proposed to derive PAC safety guarantees. The properties and comparative advantages of these three methods are thoroughly discussed. Finally, the effectiveness of the proposed methods are demonstrated through several numerical examples. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_05549 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PAC One-Step Safety Certification for Black-Box Discrete-Time Stochastic Systems Wu, Taoran Wagner, Dominik Pan, Jingduo Ong, Luke Easwaran, Arvind Xue, Bai Systems and Control This paper investigates the problem of safety certification for black-box discrete-time stochastic systems, where both the system dynamics and disturbance distributions are unknown, and only sampled data are available. Under such limited information, ensuring robust or classical quantitative safety over finite or infinite horizons is generally infeasible. To address this challenge, we propose a data-driven framework that provides theoretical one-step safety guarantees in the Probably Approximately Correct (PAC) sense. This one-step guarantee can be applied recursively at each time step, thereby yielding step-by-step safety assurances over extended horizons. Our approach formulates barrier certificate conditions based solely on sampled data and establishes PAC safety guarantees by leveraging the VC dimension, scenario approaches, Markov's inequality, and Hoeffding's inequality. Two sampling procedures are proposed, and three methods are proposed to derive PAC safety guarantees. The properties and comparative advantages of these three methods are thoroughly discussed. Finally, the effectiveness of the proposed methods are demonstrated through several numerical examples. |
| title | PAC One-Step Safety Certification for Black-Box Discrete-Time Stochastic Systems |
| topic | Systems and Control |
| url | https://arxiv.org/abs/2512.05549 |