Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator
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_ | 1866915483858501632 |
|---|---|
| author | Zhang, Haichao Yu, Haonan Zhao, Le Choi, Andrew Bai, Qinxun Yang, Yiqing Xu, Wei |
| author_facet | Zhang, Haichao Yu, Haonan Zhao, Le Choi, Andrew Bai, Qinxun Yang, Yiqing Xu, Wei |
| contents | Quadruped-based mobile manipulation presents significant challenges in robotics due to the diversity of required skills, the extended task horizon, and partial observability. After presenting a multi-stage pick-and-place task as a succinct yet sufficiently rich setup that captures key desiderata for quadruped-based mobile manipulation, we propose an approach that can train a visuo-motor policy entirely in simulation, and achieve nearly 80\% success in the real world. The policy efficiently performs search, approach, grasp, transport, and drop into actions, with emerged behaviors such as re-grasping and task chaining. We conduct an extensive set of real-world experiments with ablation studies highlighting key techniques for efficient training and effective sim-to-real transfer. Additional experiments demonstrate deployment across a variety of indoor and outdoor environments. Demo videos and additional resources are available on the project page: https://horizonrobotics.github.io/gail/SLIM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_03859 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator Zhang, Haichao Yu, Haonan Zhao, Le Choi, Andrew Bai, Qinxun Yang, Yiqing Xu, Wei Robotics Quadruped-based mobile manipulation presents significant challenges in robotics due to the diversity of required skills, the extended task horizon, and partial observability. After presenting a multi-stage pick-and-place task as a succinct yet sufficiently rich setup that captures key desiderata for quadruped-based mobile manipulation, we propose an approach that can train a visuo-motor policy entirely in simulation, and achieve nearly 80\% success in the real world. The policy efficiently performs search, approach, grasp, transport, and drop into actions, with emerged behaviors such as re-grasping and task chaining. We conduct an extensive set of real-world experiments with ablation studies highlighting key techniques for efficient training and effective sim-to-real transfer. Additional experiments demonstrate deployment across a variety of indoor and outdoor environments. Demo videos and additional resources are available on the project page: https://horizonrobotics.github.io/gail/SLIM. |
| title | Learning Multi-Stage Pick-and-Place with a Legged Mobile Manipulator |
| topic | Robotics |
| url | https://arxiv.org/abs/2509.03859 |