New k-NBCs enhance safety for unknown nonlinear systems

Researchers have developed k-inductive neural barrier certificates (k-NBCs) to enhance safety guarantees for nonlinear systems with unknown dynamics. This method relaxes traditional safety constraints by allowing temporary increases in a barrier function, up to k-1 times within a threshold, while ensuring overall system safety. The approach utilizes neural networks for scalability and integrates counterexample-guided inductive synthesis with satisfiability modulo theories for verification, using a single state trajectory to construct data-driven system models. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Introduces a novel method for verifiable safety in AI systems with unknown dynamics.

RANK_REASON Academic paper detailing a new method for system safety. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• k-inductive neural barrier certificates
• neural networks
• satisfiability modulo theories
• Willems et al.'s fundamental lemma

• paper
• safety