Newest papers

Enumeration-Guided Training of Neural Hamilton-Jacobi Safety Certificates

Mihaela-Larisa Clement, Tosca Pierro, Ezio Bartocci, Luca Marzari · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27870 · cited by 0 works (OpenAlex) · open-access PDF

Russian

Анализ достижимости Hamilton-Jacobi (HJ) предлагает формальные гарантии безопасности для систем управления, но обучение точных нейронных сертификатов остается затруднительным, особенно когда небезопасные регионы трудно характеризовать. Мы предлагаем структуру обучения, ориентированную на проверку, которая решает этот вопрос с использованием вероятностного перечисления ограничений безопасности для выявления нарушений вперед-неизменности, то есть состояний, в которых выученный сертификат неправильно классифицирует небезопасное поведение. Это производит компактный, целенаправленный набор контрэкземпляров, который более точно улавливает границу неудачи, чем входы, генерируемые стандартными методами атаки противника. Решающим образом, используя это представление для тонкого настройки предварительно обученного значения HJ

Machine translation (Meta M2M100); the English original follows.

Abstract

Hamilton-Jacobi (HJ) reachability analysis offers formal safety guarantees for control systems, but training accurate neural certificates remains difficult, particularly when unsafe regions are hard to characterize. We propose a verification-guided training framework that addresses this by using probabilistic enumeration of safety constraints to detect forward-invariance violations, i.e., states where the learned certificate incorrectly classifies unsafe behavior. This produces a compact, targeted set of counterexamples that more precisely captures the failure boundary than inputs generated by standard adversarial attack methods. Crucially, using this representation to fine-tune a pretrained HJ value function yields larger certified regions and reduces certification time across all tested benchmarks. We further introduce a shielding mechanism based on the refined certificates to enforce safety constraints at deployment time. We evaluate the proposed safety filter in a realistic, physics-based Isaac Sim environment and through real-world autonomous racing experiments, achieving zero safety constraint violations compared to a nominal controller and a backup policy based on Linear Quadratic Regulation (LQR). These results demonstrate the effectiveness of the proposed shielding mechanism in ensuring safe operation under high-speed, safety-critical conditions.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Certification, Probabilistic logic, Backup, Certificate, System safety

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27870, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange