Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911643385987072 |
|---|---|
| author | Kranzlmüller, Miriam Koller, Lukas Ladner, Tobias Althoff, Matthias |
| author_facet | Kranzlmüller, Miriam Koller, Lukas Ladner, Tobias Althoff, Matthias |
| contents | Barrier certificates are scalar functions over the state space of dynamical systems that separate all unsafe states from all reachable states. The existence of a barrier certificate formally verifies the safety of the dynamical system. Recent approaches synthesize barrier certificates by iteratively training a neural network. In each iteration, the candidate is formally verified - if successful, the barrier certificate is found. Instead, we propose a set-based training approach that tightly integrates verification into training via a set-based loss function that soundly encodes all barrier certificate properties. A loss of zero formally proves the validity of the barrier certificate, collapsing the iterative training and verification into a single training procedure. Our experiments demonstrate that our set-based training approach scales well with the system dimension and naturally handles complex nonlinear dynamics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02526 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems Kranzlmüller, Miriam Koller, Lukas Ladner, Tobias Althoff, Matthias Systems and Control Artificial Intelligence Barrier certificates are scalar functions over the state space of dynamical systems that separate all unsafe states from all reachable states. The existence of a barrier certificate formally verifies the safety of the dynamical system. Recent approaches synthesize barrier certificates by iteratively training a neural network. In each iteration, the candidate is formally verified - if successful, the barrier certificate is found. Instead, we propose a set-based training approach that tightly integrates verification into training via a set-based loss function that soundly encodes all barrier certificate properties. A loss of zero formally proves the validity of the barrier certificate, collapsing the iterative training and verification into a single training procedure. Our experiments demonstrate that our set-based training approach scales well with the system dimension and naturally handles complex nonlinear dynamics. |
| title | Set-Based Training of Neural Barrier Certificates for Safety Verification of Dynamical Systems |
| topic | Systems and Control Artificial Intelligence |
| url | https://arxiv.org/abs/2605.02526 |