Learning-based methods for constructing control barrier functions (CBFs) are gaining popularity for ensuring safe robot control. A major limitation of existing methods is their reliance on extensive sampling over the state space or online system interaction in simulation. In this work we propose a novel framework for learning neural CBFs through a fixed, sparsely-labeled dataset collected prior to training. Our approach introduces new annotation techniques based on out-of-distribution analysis, enabling efficient knowledge propagation from the limited labeled data to the unlabeled data. We also eliminate the dependency on a high-performance expert controller, and allow multiple sub-optimal policies or even manual control during data collection. We evaluate the proposed method on real-world platforms. With limited amount of offline data, it achieves state-of-the-art performance for dynamic obstacle avoidance, demonstrating statistically safer and less conservative maneuvers compared to existing methods.
View on arXiv@article{yu2025_2503.10641,
title={ Estimating Control Barriers from Offline Data },
author={ Hongzhan Yu and Seth Farrell and Ryo Yoshimitsu and Zhizhen Qin and Henrik I. Christensen and Sicun Gao },
journal={arXiv preprint arXiv:2503.10641},
year={ 2025 }
}