TamedPUMA: safe and stable imitation learning with geometric fabrics
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_ | 1866915209108520960 |
|---|---|
| author | Bakker, Saray Pérez-Dattari, Rodrigo Della Santina, Cosimo Böhmer, Wendelin Alonso-Mora, Javier |
| author_facet | Bakker, Saray Pérez-Dattari, Rodrigo Della Santina, Cosimo Böhmer, Wendelin Alonso-Mora, Javier |
| contents | Using the language of dynamical systems, Imitation learning (IL) provides an intuitive and effective way of teaching stable task-space motions to robots with goal convergence. Yet, IL techniques are affected by serious limitations when it comes to ensuring safety and fulfillment of physical constraints. With this work, we solve this challenge via TamedPUMA, an IL algorithm augmented with a recent development in motion generation called geometric fabrics. As both the IL policy and geometric fabrics describe motions as artificial second-order dynamical systems, we propose two variations where IL provides a navigation policy for geometric fabrics. The result is a stable imitation learning strategy within which we can seamlessly blend geometrical constraints like collision avoidance and joint limits. Beyond providing a theoretical analysis, we demonstrate TamedPUMA with simulated and real-world tasks, including a 7-DoF manipulator. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_17432 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TamedPUMA: safe and stable imitation learning with geometric fabrics Bakker, Saray Pérez-Dattari, Rodrigo Della Santina, Cosimo Böhmer, Wendelin Alonso-Mora, Javier Systems and Control Machine Learning Robotics Using the language of dynamical systems, Imitation learning (IL) provides an intuitive and effective way of teaching stable task-space motions to robots with goal convergence. Yet, IL techniques are affected by serious limitations when it comes to ensuring safety and fulfillment of physical constraints. With this work, we solve this challenge via TamedPUMA, an IL algorithm augmented with a recent development in motion generation called geometric fabrics. As both the IL policy and geometric fabrics describe motions as artificial second-order dynamical systems, we propose two variations where IL provides a navigation policy for geometric fabrics. The result is a stable imitation learning strategy within which we can seamlessly blend geometrical constraints like collision avoidance and joint limits. Beyond providing a theoretical analysis, we demonstrate TamedPUMA with simulated and real-world tasks, including a 7-DoF manipulator. |
| title | TamedPUMA: safe and stable imitation learning with geometric fabrics |
| topic | Systems and Control Machine Learning Robotics |
| url | https://arxiv.org/abs/2503.17432 |