Learning-Based Underwater Autonomous Grasping via 3D Point Cloud
文献类型：会议论文
| 作者 | Wang C(王聪)2,3,4,5; Zhang QF(张奇峰)2,3,4 ; Li S(李硕); (1,2,3); Wang XH(王晓辉)2,3,4; Lane, David1; Petillot, Yvan1; Wang, Sen1
|
| 出版日期 | 2021 |
| 会议日期 | September 20-23, 2021 |
| 会议地点 | San Diego, CA, United states |
| 关键词 | Grasp Pose Detection (GPD) underwater grasping stereo camera 3D point cloud |
| 页码 | 1-5 |
| 英文摘要 | Underwater autonomous grasping is a challenging task for robotic research. In this paper, we propose a learning-based underwater grasping method using 3D point cloud generated from an underwater stereo camera. First, we use Pinax-model for accurate refraction correction of a stereo camera in a flat-pane housing. Second, dense point cloud of the target is generated using the calibrated stereo images. An improved Grasp Pose Detection (GPD) method is then developed to generate the candidate grasping poses and select the best one based on kinematic constraints. Finally, an optimal trajectory is planned to finish the grasping task. Experiments in a water tank have proved the effectiveness of our method. |
| 产权排序 | 1 |
| 会议录 | OCEANS 2021: San Diego - Porto
 |
| 会议录出版者 | IEEE |
| 会议录出版地 | New York |
| 语种 | 英语 |
| ISSN号 | 0197-7385 |
| ISBN号 | 978-0-6929-3559-0 |
| 源URL | [http://ir.sia.cn/handle/173321/30580]  |
| 专题 | 沈阳自动化研究所_水下机器人研究室 |
| 通讯作者 | Zhang QF(张奇峰) |
| 作者单位 | 1.Heriot-Watt University, Edinburgh Centre for Robotics, United Kingdom 2.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016, China 3.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences, Shenyang 110169, China 4.Key Laboratory of Marine Robotics, Shenyang 110169, China 5.University of Chinese Academy of Sciences, Beijing 100049, China |
| 推荐引用方式 GB/T 7714 | Wang C,Zhang QF,Li S,et al. Learning-Based Underwater Autonomous Grasping via 3D Point Cloud[C]. 见:. San Diego, CA, United states. September 20-23, 2021. |
入库方式： OAI收割
来源：沈阳自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。