Robotic Grasping through Combined image-Based Grasp Proposal and 3D Reconstruction

03/03/2020
by   Tarik Tosun, et al.
0

We present a novel approach to robotic grasp planning using both a learned grasp proposal network and a learned 3D shape reconstruction network. Our system generates 6-DOF grasps from a single RGB-D image of the target object, which is provided as input to both networks. By using the geometric reconstruction to refine the the candidate grasp produced by the grasp proposal network, our system is able to accurately grasp both known and unknown objects, even when the grasp location on the object is not visible in the input image. This paper presents the network architectures, training procedures, and grasp refinement method that comprise our system. Hardware experiments demonstrate the efficacy of our system at grasping both known and unknown objects (91 success rate). We additionally perform ablation studies that show the benefits of combining a learned grasp proposal with geometric reconstruction for grasping, and also show that our system outperforms several baselines in a grasping task.

READ FULL TEXT
research
10/02/2019

Learning Continuous 3D Reconstructions for Geometrically Aware Grasping

Deep learning has enabled remarkable improvements in grasp synthesis for...
research
09/14/2021

Object Shell Reconstruction: Camera-centric Object Representation for Robotic Grasping

Robots can effectively grasp and manipulate objects using their 3D model...
research
05/13/2020

Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data

This paper introduces Action Image, a new grasp proposal representation ...
research
07/22/2019

A novel object slicing based grasp planner for 3D object grasping using underactuated robot gripper

Robotic grasping of arbitrary objects even in completely known environme...
research
04/01/2021

A Joint Network for Grasp Detection Conditioned on Natural Language Commands

We consider the task of grasping a target object based on a natural lang...
research
09/05/2016

Classifying and sorting cluttered piles of unknown objects with robots: a learning approach

We consider the problem of sorting a densely cluttered pile of unknown o...
research
01/15/2020

DGCM-Net: Dense Geometrical Correspondence Matching Network for Incremental Experience-based Robotic Grasping

This article presents a method for grasping novel objects by learning fr...

Please sign up or login with your details

Forgot password? Click here to reset