Towards Safe Robot Foundation Models
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910867495321600 |
|---|---|
| author | Tölle, Maximilian Gruner, Theo Palenicek, Daniel Günster, Jonas Liu, Puze Watson, Joe Tateo, Davide Peters, Jan |
| author_facet | Tölle, Maximilian Gruner, Theo Palenicek, Daniel Günster, Jonas Liu, Puze Watson, Joe Tateo, Davide Peters, Jan |
| contents | Robot foundation models hold the potential for deployment across diverse environments, from industrial applications to household tasks. While current research focuses primarily on the policies' generalization capabilities across a variety of tasks, it fails to address safety, a critical requirement for deployment on real-world systems. In this paper, we introduce a safety layer designed to constrain the action space of any generalist policy appropriately. Our approach uses ATACOM, a safe reinforcement learning algorithm that creates a safe action space and, therefore, ensures safe state transitions. By extending ATACOM to generalist policies, our method facilitates their deployment in safety-critical scenarios without requiring any specific safety fine-tuning. We demonstrate the effectiveness of this safety layer in an air hockey environment, where it prevents a puck-hitting agent from colliding with its surroundings, a failure observed in generalist policies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07404 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Safe Robot Foundation Models Tölle, Maximilian Gruner, Theo Palenicek, Daniel Günster, Jonas Liu, Puze Watson, Joe Tateo, Davide Peters, Jan Robotics Robot foundation models hold the potential for deployment across diverse environments, from industrial applications to household tasks. While current research focuses primarily on the policies' generalization capabilities across a variety of tasks, it fails to address safety, a critical requirement for deployment on real-world systems. In this paper, we introduce a safety layer designed to constrain the action space of any generalist policy appropriately. Our approach uses ATACOM, a safe reinforcement learning algorithm that creates a safe action space and, therefore, ensures safe state transitions. By extending ATACOM to generalist policies, our method facilitates their deployment in safety-critical scenarios without requiring any specific safety fine-tuning. We demonstrate the effectiveness of this safety layer in an air hockey environment, where it prevents a puck-hitting agent from colliding with its surroundings, a failure observed in generalist policies. |
| title | Towards Safe Robot Foundation Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2503.07404 |