Learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910581781430272 |
|---|---|
| author | Pitz, Johannes Röstel, Lennart Sievers, Leon Burschka, Darius Bäuml, Berthold |
| author_facet | Pitz, Johannes Röstel, Lennart Sievers, Leon Burschka, Darius Bäuml, Berthold |
| contents | Reorienting diverse objects with a multi-fingered hand is a challenging task. Current methods in robotic in-hand manipulation are either object-specific or require permanent supervision of the object state from visual sensors. This is far from human capabilities and from what is needed in real-world applications. In this work, we address this gap by training shape-conditioned agents to reorient diverse objects in hand, relying purely on tactile feedback (via torque and position measurements of the fingers' joints). To achieve this, we propose a learning framework that exploits shape information in a reinforcement learning policy and a learned state estimator. We find that representing 3D shapes by vectors from a fixed set of basis points to the shape's surface, transformed by its predicted 3D pose, is especially helpful for learning dexterous in-hand manipulation. In simulation and real-world experiments, we show the reorientation of many objects with high success rates, on par with state-of-the-art results obtained with specialized single-object agents. Moreover, we show generalization to novel objects, achieving success rates of $\sim$90% even for non-convex shapes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_18834 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects Pitz, Johannes Röstel, Lennart Sievers, Leon Burschka, Darius Bäuml, Berthold Robotics Reorienting diverse objects with a multi-fingered hand is a challenging task. Current methods in robotic in-hand manipulation are either object-specific or require permanent supervision of the object state from visual sensors. This is far from human capabilities and from what is needed in real-world applications. In this work, we address this gap by training shape-conditioned agents to reorient diverse objects in hand, relying purely on tactile feedback (via torque and position measurements of the fingers' joints). To achieve this, we propose a learning framework that exploits shape information in a reinforcement learning policy and a learned state estimator. We find that representing 3D shapes by vectors from a fixed set of basis points to the shape's surface, transformed by its predicted 3D pose, is especially helpful for learning dexterous in-hand manipulation. In simulation and real-world experiments, we show the reorientation of many objects with high success rates, on par with state-of-the-art results obtained with specialized single-object agents. Moreover, we show generalization to novel objects, achieving success rates of $\sim$90% even for non-convex shapes. |
| title | Learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects |
| topic | Robotics |
| url | https://arxiv.org/abs/2407.18834 |