Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Grasp Pose Detection in Point Clouds

About

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 a significant 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.

Andreas ten Pas, Marcus Gualtieri, Kate Saenko, Robert Platt• 2017

Related benchmarks

TaskDatasetResultRank
Grasp DetectionGraspNet-1Billion (RealSense)
AP (Average)17.48
32
Grasp DetectionGraspNet-1Billion RealSense (Seen)
AP22.87
25
Grasp DetectionGraspNet-1Billion RealSense Similar
AP0.2133
25
Grasp DetectionGraspNet-1Billion RealSense Novel
AP8.24
25
Grasp DetectionGraspNet-1Billion Kinect camera (seen)
AP29.65
23
Grasp DetectionGraspNet-1Billion Kinect camera (Novel)
AP9.58
13
Grasp DetectionGraspNet-1Billion Kinect camera (Similar split)
AP0.2318
13
Grasp Pose DetectionGraspNet-1Billion RealSense 1.0 (Seen)
AP28.16
10
Grasp Pose DetectionGraspNet-1Billion Similar RealSense 1.0
AP26.47
10
Grasp Pose DetectionGraspNet-1Billion Kinect 1.0 (Similar)
AP28.19
10
Showing 10 of 17 rows

Other info

Follow for update