Grasp Pose Detection in Point Clouds
Grasp Pose Detection in Point Clouds
复制标题
DOI：
10.1177/0278364917735594
复制
发表时间：
2017-12-01
影响因子：
9.2
通讯作者：
Platt, Robert
中科院分区：
文献类型：
--
作者：
ten Pas, Andreas;Gualtieri, Marcus;Platt, Robert
最近，已经提出了一些把握检测方法，可以用来本地化机器人把握配置直接从传感器数据，而不估计对象的姿态。其基本思想是将抓握感知类似于计算机视觉中的物体检测。这些方法将噪声和部分遮挡的RGBD图像或点云作为输入，并产生可行抓握的输出姿态估计，而无需假设对象的已知CAD模型。虽然这些方法可以很好地将掌握的知识推广到新的对象，但它们还没有被证明足够可靠以广泛使用。许多抓取检测方法对于孤立或光杂波中呈现的新对象实现了75%到95%之间的抓取成功率（抓取成功率作为抓取尝试总数的一部分）。这些成功率不仅对于实际抓取应用来说太低，而且所评估的轻杂波场景通常不能反映现实世界的抓取现实。本文提出了一些创新，共同导致在把握检测性能的改善。由于我们的每一个贡献的性能的具体改善是定量测量无论是在模拟或机器人硬件。最终，我们报告了一系列机器人实验，平均93%的端到端的把握成功率为密集杂乱的新对象。
Recently, a number of grasp detection methods have been proposed that can be used to localize robotic grasp configurations directly from sensor data without estimating object pose. The underlying idea is to treat grasp perception analogously to object detection in computer vision. These methods take as input a noisy and partially occluded RGBD image or point cloud and produce as output pose estimates of viable grasps, without assuming a known CAD model of the object. Although these methods generalize grasp knowledge to new objects well, they have not yet been demonstrated to be reliable enough for wide use. Many grasp detection methods achieve grasp success rates (grasp successes as a fraction of the total number of grasp attempts) between 75% and 95% for novel objects presented in isolation or in light clutter. Not only are these success rates too low for practical grasping applications, but the light clutter scenarios that are evaluated often do not reflect the realities of real-world grasping. This paper proposes a number of innovations that together result in an improvement in grasp detection performance. The specific improvement in performance due to each of our contributions is quantitatively measured either in simulation or on robotic hardware. Ultimately, we report a series of robotic experiments that average a 93% end-to-end grasp success rate for novel objects presented in dense clutter.