Estimating Control Barriers from Offline Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917956621959168 |
|---|---|
| author | Yu, Hongzhan Farrell, Seth Yoshimitsu, Ryo Qin, Zhizhen Christensen, Henrik I. Gao, Sicun |
| author_facet | Yu, Hongzhan Farrell, Seth Yoshimitsu, Ryo Qin, Zhizhen Christensen, Henrik I. Gao, Sicun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_10641 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Estimating Control Barriers from Offline Data Yu, Hongzhan Farrell, Seth Yoshimitsu, Ryo Qin, Zhizhen Christensen, Henrik I. Gao, Sicun Systems and Control Artificial Intelligence Robotics 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. |
| title | Estimating Control Barriers from Offline Data |
| topic | Systems and Control Artificial Intelligence Robotics |
| url | https://arxiv.org/abs/2503.10641 |