期刊
JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS
卷 100, 期 3-4, 页码 791-808出版社
SPRINGER
DOI: 10.1007/s10846-020-01236-7
关键词
Switching scheme; Pose estimation; Robotic grasping; Deep learning; Occlusion-aware
资金
- National Natural Science Foundation of China [51675329, 51675342, 51775332]
- Innovative Methods Program of Ministry of Science and Technology of China [2015IM010100]
- National Key Scientific Instruments and Equipment Development Program of China [2016YFF0101602]
- Shanghai Committee of Science and Technology [15142200800, 16441906000, 16XD1425000]
- State Key Laboratory of Smart Manufacturing for Special Vehicles and Transmission System [GZ2016KF001]
Real-time vision-based robotic grasping is challenging in clutter. In such scene, the target object should be perceived accurately, where it may be occluded and misrecognized by many distractors including irrelevant objects and the robotic arm. In addition, the limited field of view (FOV) of camera makes it prone for objects to get out of the camera view. We develop a novel camera fusion method of pose estimation based on switching scheme for real-time robotic grasping under hybrid eye-in-hand (EIH)/eye-to-hand (ETH) configurations. The objects are locked based on occlusion-aware object detection to apply switching function for single pose estimation or multiple vision fusion. This method improves the accuracy of pose estimation and robustness of dynamic grasping under occlusion. Experimental results on pose estimation and real-time robotic grasping in clutter verify the effectiveness of the proposed method.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据