MeshDMP: Motion Planning on Discrete Manifolds using Dynamic Movement Primitives
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910805510848512 |
|---|---|
| author | Vedove, Matteo Dalle Abu-Dakka, Fares J. Palopoli, Luigi Fontanelli, Daniele Saveriano, Matteo |
| author_facet | Vedove, Matteo Dalle Abu-Dakka, Fares J. Palopoli, Luigi Fontanelli, Daniele Saveriano, Matteo |
| contents | An open problem in industrial automation is to reliably perform tasks requiring in-contact movements with complex workpieces, as current solutions lack the ability to seamlessly adapt to the workpiece geometry. In this paper, we propose a Learning from Demonstration approach that allows a robot manipulator to learn and generalise motions across complex surfaces by leveraging differential mathematical operators on discrete manifolds to embed information on the geometry of the workpiece extracted from triangular meshes, and extend the Dynamic Movement Primitives (DMPs) framework to generate motions on the mesh surfaces. We also propose an effective strategy to adapt the motion to different surfaces, by introducing an isometric transformation of the learned forcing term. The resulting approach, namely MeshDMP, is evaluated both in simulation and real experiments, showing promising results in typical industrial automation tasks like car surface polishing. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_15123 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MeshDMP: Motion Planning on Discrete Manifolds using Dynamic Movement Primitives Vedove, Matteo Dalle Abu-Dakka, Fares J. Palopoli, Luigi Fontanelli, Daniele Saveriano, Matteo Robotics An open problem in industrial automation is to reliably perform tasks requiring in-contact movements with complex workpieces, as current solutions lack the ability to seamlessly adapt to the workpiece geometry. In this paper, we propose a Learning from Demonstration approach that allows a robot manipulator to learn and generalise motions across complex surfaces by leveraging differential mathematical operators on discrete manifolds to embed information on the geometry of the workpiece extracted from triangular meshes, and extend the Dynamic Movement Primitives (DMPs) framework to generate motions on the mesh surfaces. We also propose an effective strategy to adapt the motion to different surfaces, by introducing an isometric transformation of the learned forcing term. The resulting approach, namely MeshDMP, is evaluated both in simulation and real experiments, showing promising results in typical industrial automation tasks like car surface polishing. |
| title | MeshDMP: Motion Planning on Discrete Manifolds using Dynamic Movement Primitives |
| topic | Robotics |
| url | https://arxiv.org/abs/2410.15123 |