High precision grasp pose detection in dense clutter

Abstract

Abstract-This paper considers the problem of grasp pose detection in point clouds. We follow a general algorithmic structure that first generates a large set of 6-DOF grasp candidates and then classifies each of them as a good or a bad grasp. Our focus in this paper is on improving the second step by using depth sensor scans from large online datasets to train a convolutional neural network. We propose two new representations of grasp candidates, and we quantify the effect of using prior knowledge of two forms: instance or category knowledge of the object to be grasped, and pretraining the network on simulated depth data obtained from idealized CAD models. Our analysis shows that a more informative grasp candidate representation as well as pretraining and prior knowledge significantly improve grasp detection. We evaluate our approach on a Baxter Research Robot and demonstrate an average grasp success rate of 93% in dense clutter. This is a 20% improvement compared to our prior work.

Learning One-Shot Imitation From Humans Without Humans

“…Rather than directly operating on randomised images, RCAN [8] is a recent approach that instead translate randomised rendered images into their equivalent non-randomised, canonical versions, producing superior results on a complex sim-to-real grasping task. Rather than operating on RGB images, other works have instead used depth images to cross the domain gap [37], [38]; however, in our tasks, the colour of an object is an important feature when inferring what object the robot needs to interact with, particularly when the geometry of the objects are very similar. In our work, we show that domain randomisation can be leveraged to transfer the ability to infer actions from human demonstrations.…”

Self-supervised 3D Shape and Viewpoint Estimation from Single Images for Robotics

“…To exemplify the ability of our approach to improve grasping performance we use a PR2 robot to perform grasps planned by using Grasp Pose Detection (GPD) [32], which predicts a series of 6-DOF candidate grasp poses given a 3D point cloud for a 2-finger grasp. The reachability of the proposed candidate grasps are checked using MoveIt!…”

GlassLoc: Plenoptic Grasp Pose Detection in Transparent Clutter

“…Since we have three types of features and three axes to project, we have nine channels in total. For classifier, we use the LeNet [11] structure which is a common structure for grasp pose classification and ranking [7], [10]. The output of the classifier is the binary label {graspable, not graspable} associated with the confidence scores.…”