AI RESEARCH
Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation
arXiv CS.LG
•
ArXi:2511.06341v2 Announce Type: replace Control barrier functions (CBFs) are a popular tool for safety certification of nonlinear dynamical control systems. Recently, CBFs represented as neural networks have shown great promise due to their expressiveness and applicability to a broad class of dynamics and safety constraints. However, verifying that a trained neural network is indeed a valid CBF is a computational bottleneck that limits the size of the networks that can be used.