Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D input
Keypoint-GraspNet: Keypoint-based 6-DoF Grasp Generation from the Monocular RGB-D input
复制标题
DOI：
10.1109/icra48891.2023.10161284
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Yiye Chen;Yunzhi Lin;P. Vela
中科院分区：
文献类型：
--
作者：
Yiye Chen;Yunzhi Lin;P. Vela
使用点云输入的6自由度抓取学习的成功受到计算成本的影响，这些计算成本来自于它们的无序性质和将点云减少到可管理大小的预处理需求。这些属性导致在具有低点云基数的小对象上失败。这篇手稿探索了直接从RGB-D图像输入生成抓取，而不是点云。该方法称为Keypoint-GraspNet（KGN），通过检测图像中投影的抓手关键点，然后使用$\mathrm{P}n\mathrm {P}$算法恢复其SE（3）姿势，在感知空间中运行。网络的训练涉及从具有已知连续抓取家族的原始形状对象导出的合成数据集。Keypoint-GraspNet仅使用单对象合成数据进行训练，在我们的单对象数据集上实现了上级结果，在多对象测试集上与最先进的基线具有可比性，并且在小对象上优于最具竞争力的基线。Keypoint-GraspNet比经过测试的点云方法快3倍以上。机器人实验显示出很高的成功率，证明了KGN的实用潜力。
The success of 6-DoF grasp learning with point cloud input is tempered by the computational costs resulting from their unordered nature and pre-processing needs for reducing the point cloud to a manageable size. These properties lead to failure on small objects with low point cloud cardinality. Instead of point clouds, this manuscript explores grasp generation directly from the RGB-D image input. The approach, called Keypoint-GraspNet (KGN), operates in perception space by detecting projected gripper keypoints in the image, then recovering their SE(3) poses with a $\mathrm{P}n\mathrm{P}$ algorithm. Training of the network involves a synthetic dataset derived from primitive shape objects with known continuous grasp families. Trained with only single-object synthetic data, Keypoint-GraspNet achieves superior result on our single-object dataset, comparable performance with state-of-art baselines on a multi-object test set, and outperforms the most competitive baseline on small objects. Keypoint-GraspNet is more than 3x faster than tested point cloud methods. Robot experiments show high success rate, demonstrating KGN's practical potential.