Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2022
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910542237532160 |
|---|---|
| author | Horváth, Dániel Bocsi, Kristóf Erdős, Gábor Istenes, Zoltán |
| author_facet | Horváth, Dániel Bocsi, Kristóf Erdős, Gábor Istenes, Zoltán |
| contents | Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent deep-learning-based models show promising results, they require an immense dataset for training. In this paper, two vision-based, multi-object grasp pose estimation models (MOGPE), the MOGPE Real-Time and the MOGPE High-Precision are proposed. Furthermore, a sim2real method based on domain randomization to diminish the reality gap and overcome the data shortage. Our methods yielded an 80% and a 96.67% success rate in a real-world robotic pick-and-place experiment, with the MOGPE Real-Time and the MOGPE High-Precision model respectively. Our framework provides an industrial tool for fast data generation and model training and requires minimal domain-specific data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_01048 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications Horváth, Dániel Bocsi, Kristóf Erdős, Gábor Istenes, Zoltán Robotics Adaptive robotics plays an essential role in achieving truly co-creative cyber physical systems. In robotic manipulation tasks, one of the biggest challenges is to estimate the pose of given workpieces. Even though the recent deep-learning-based models show promising results, they require an immense dataset for training. In this paper, two vision-based, multi-object grasp pose estimation models (MOGPE), the MOGPE Real-Time and the MOGPE High-Precision are proposed. Furthermore, a sim2real method based on domain randomization to diminish the reality gap and overcome the data shortage. Our methods yielded an 80% and a 96.67% success rate in a real-world robotic pick-and-place experiment, with the MOGPE Real-Time and the MOGPE High-Precision model respectively. Our framework provides an industrial tool for fast data generation and model training and requires minimal domain-specific data. |
| title | Sim2Real Grasp Pose Estimation for Adaptive Robotic Applications |
| topic | Robotics |
| url | https://arxiv.org/abs/2211.01048 |