Safety filtering of robotic manipulation under environment uncertainty: a computational approach
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866918141663117312 |
|---|---|
| author | Johansson, Anna Lindmark, Daniel Wiberg, Viktor Servin, Martin |
| author_facet | Johansson, Anna Lindmark, Daniel Wiberg, Viktor Servin, Martin |
| contents | Robotic manipulation in dynamic and unstructured environments requires safety mechanisms that exploit what is known and what is uncertain about the world. Existing safety filters often assume full observability, limiting their applicability in real-world tasks. We propose a physics-based safety filtering scheme that leverages high-fidelity simulation to assess control policies under uncertainty in world parameters. The method combines dense rollout with nominal parameters and parallelizable sparse re-evaluation at critical state-transitions, quantified through generalized factors of safety for stable grasping and actuator limits, and targeted uncertainty reduction through probing actions. We demonstrate the approach in a simulated bimanual manipulation task with uncertain object mass and friction, showing that unsafe trajectories can be identified and filtered efficiently. Our results highlight physics-based sparse safety evaluation as a scalable strategy for safe robotic manipulation under uncertainty. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_12674 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Safety filtering of robotic manipulation under environment uncertainty: a computational approach Johansson, Anna Lindmark, Daniel Wiberg, Viktor Servin, Martin Robotics Robotic manipulation in dynamic and unstructured environments requires safety mechanisms that exploit what is known and what is uncertain about the world. Existing safety filters often assume full observability, limiting their applicability in real-world tasks. We propose a physics-based safety filtering scheme that leverages high-fidelity simulation to assess control policies under uncertainty in world parameters. The method combines dense rollout with nominal parameters and parallelizable sparse re-evaluation at critical state-transitions, quantified through generalized factors of safety for stable grasping and actuator limits, and targeted uncertainty reduction through probing actions. We demonstrate the approach in a simulated bimanual manipulation task with uncertain object mass and friction, showing that unsafe trajectories can be identified and filtered efficiently. Our results highlight physics-based sparse safety evaluation as a scalable strategy for safe robotic manipulation under uncertainty. |
| title | Safety filtering of robotic manipulation under environment uncertainty: a computational approach |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.12674 |