Placeit! A Framework for Learning Robot Object Placement Skills
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_ | 1866911202441953280 |
|---|---|
| author | Ferrad, Amina Huber, Johann Hélénon, François Gleyze, Julien Khoramshahi, Mahdi Doncieux, Stéphane |
| author_facet | Ferrad, Amina Huber, Johann Hélénon, François Gleyze, Julien Khoramshahi, Mahdi Doncieux, Stéphane |
| contents | Robotics research has made significant strides in learning, yet mastering basic skills like object placement remains a fundamental challenge. A key bottleneck is the acquisition of large-scale, high-quality data, which is often a manual and laborious process. Inspired by Graspit!, a foundational work that used simulation to automatically generate dexterous grasp poses, we introduce Placeit!, an evolutionary-computation framework for generating valid placement positions for rigid objects. Placeit! is highly versatile, supporting tasks from placing objects on tables to stacking and inserting them. Our experiments show that by leveraging quality-diversity optimization, Placeit! significantly outperforms state-of-the-art methods across all scenarios for generating diverse valid poses. A pick&place pipeline built on our framework achieved a 90% success rate over 120 real-world deployments. This work positions Placeit! as a powerful tool for open-environment pick-and-place tasks and as a valuable engine for generating the data needed to train simulation-based foundation models in robotics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_09267 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Placeit! A Framework for Learning Robot Object Placement Skills Ferrad, Amina Huber, Johann Hélénon, François Gleyze, Julien Khoramshahi, Mahdi Doncieux, Stéphane Robotics Machine Learning Robotics research has made significant strides in learning, yet mastering basic skills like object placement remains a fundamental challenge. A key bottleneck is the acquisition of large-scale, high-quality data, which is often a manual and laborious process. Inspired by Graspit!, a foundational work that used simulation to automatically generate dexterous grasp poses, we introduce Placeit!, an evolutionary-computation framework for generating valid placement positions for rigid objects. Placeit! is highly versatile, supporting tasks from placing objects on tables to stacking and inserting them. Our experiments show that by leveraging quality-diversity optimization, Placeit! significantly outperforms state-of-the-art methods across all scenarios for generating diverse valid poses. A pick&place pipeline built on our framework achieved a 90% success rate over 120 real-world deployments. This work positions Placeit! as a powerful tool for open-environment pick-and-place tasks and as a valuable engine for generating the data needed to train simulation-based foundation models in robotics. |
| title | Placeit! A Framework for Learning Robot Object Placement Skills |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2510.09267 |