EigenSafe: A Spectral Framework for Learning-Based Probabilistic Safety Assessment
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_ | 1866915799019552768 |
|---|---|
| author | Jang, Inkyu Park, Jonghae Cho, Sihyun Mballo, Chams E. Tomlin, Claire J. Kim, H. Jin |
| author_facet | Jang, Inkyu Park, Jonghae Cho, Sihyun Mballo, Chams E. Tomlin, Claire J. Kim, H. Jin |
| contents | We present EigenSafe, an operator-theoretic framework for safety assessment of learning-enabled stochastic systems. In many robotic applications, the dynamics are inherently stochastic due to factors such as sensing noise and environmental disturbances, and it is challenging for conventional methods such as Hamilton-Jacobi reachability and control barrier functions to provide a well-calibrated safety critic that is tied to the actual safety probability. We derive a linear operator that governs the dynamic programming principle for safety probability, and find that its dominant eigenpair provides critical safety information for both individual state-action pairs and the overall closed-loop system. The proposed framework learns this dominant eigenpair, which can be used to either inform or constrain policy updates. We demonstrate that the learned eigenpair effectively facilitates safe reinforcement learning. Further, we validate its applicability in enhancing the safety of learned policies from imitation learning through robot manipulation experiments using a UR3 robotic arm in a food preparation task. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_17750 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | EigenSafe: A Spectral Framework for Learning-Based Probabilistic Safety Assessment Jang, Inkyu Park, Jonghae Cho, Sihyun Mballo, Chams E. Tomlin, Claire J. Kim, H. Jin Robotics Systems and Control Optimization and Control We present EigenSafe, an operator-theoretic framework for safety assessment of learning-enabled stochastic systems. In many robotic applications, the dynamics are inherently stochastic due to factors such as sensing noise and environmental disturbances, and it is challenging for conventional methods such as Hamilton-Jacobi reachability and control barrier functions to provide a well-calibrated safety critic that is tied to the actual safety probability. We derive a linear operator that governs the dynamic programming principle for safety probability, and find that its dominant eigenpair provides critical safety information for both individual state-action pairs and the overall closed-loop system. The proposed framework learns this dominant eigenpair, which can be used to either inform or constrain policy updates. We demonstrate that the learned eigenpair effectively facilitates safe reinforcement learning. Further, we validate its applicability in enhancing the safety of learned policies from imitation learning through robot manipulation experiments using a UR3 robotic arm in a food preparation task. |
| title | EigenSafe: A Spectral Framework for Learning-Based Probabilistic Safety Assessment |
| topic | Robotics Systems and Control Optimization and Control |
| url | https://arxiv.org/abs/2509.17750 |