Self-supervised 6-DoF Robot Grasping by Demonstration via Augmented Reality Teleoperation System
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916192257572864 |
|---|---|
| author | Dengxiong, Xiwen Wang, Xueting Bai, Shi Zhang, Yunbo |
| author_facet | Dengxiong, Xiwen Wang, Xueting Bai, Shi Zhang, Yunbo |
| contents | Most existing 6-DoF robot grasping solutions depend on strong supervision on grasp pose to ensure satisfactory performance, which could be laborious and impractical when the robot works in some restricted area. To this end, we propose a self-supervised 6-DoF grasp pose detection framework via an Augmented Reality (AR) teleoperation system that can efficiently learn human demonstrations and provide 6-DoF grasp poses without grasp pose annotations. Specifically, the system collects the human demonstration from the AR environment and contrastively learns the grasping strategy from the demonstration. For the real-world experiment, the proposed system leads to satisfactory grasping abilities and learning to grasp unknown objects within three demonstrations. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_03067 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-supervised 6-DoF Robot Grasping by Demonstration via Augmented Reality Teleoperation System Dengxiong, Xiwen Wang, Xueting Bai, Shi Zhang, Yunbo Robotics Computer Vision and Pattern Recognition Most existing 6-DoF robot grasping solutions depend on strong supervision on grasp pose to ensure satisfactory performance, which could be laborious and impractical when the robot works in some restricted area. To this end, we propose a self-supervised 6-DoF grasp pose detection framework via an Augmented Reality (AR) teleoperation system that can efficiently learn human demonstrations and provide 6-DoF grasp poses without grasp pose annotations. Specifically, the system collects the human demonstration from the AR environment and contrastively learns the grasping strategy from the demonstration. For the real-world experiment, the proposed system leads to satisfactory grasping abilities and learning to grasp unknown objects within three demonstrations. |
| title | Self-supervised 6-DoF Robot Grasping by Demonstration via Augmented Reality Teleoperation System |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.03067 |