Deep Dexterous Grasping of Novel Objects from a Single View

by   Umit Rusen Aktas, et al.

Dexterous grasping of a novel object given a single view is an open problem. This paper makes several contributions to its solution. First, we present a simulator for generating and testing dexterous grasps. Second we present a data set, generated by this simulator, of 2.4 million simulated dexterous grasps of variations of 294 base objects drawn from 20 categories. Third, we present a basic architecture for generation and evaluation of dexterous grasps that may be trained in a supervised manner. Fourth, we present three different evaluative architectures, employing ResNet-50 or VGG16 as their visual backbone. Fifth, we train, and evaluate seventeen variants of generative-evaluative architectures on this simulated data set, showing improvement from 69.53 real robot implementation and evaluate the four most promising variants, executing 196 real robot grasps in total. We show that our best architectural variant achieves a grasp success rate of 87.8 a single view, improving on a baseline of 57.1


page 1

page 5

page 10

page 11

page 12

page 13

page 14


GraspCaps: Capsule Networks Are All You Need for Grasping Familiar Objects

As robots become more accessible outside of industrial settings, the nee...

Learning better generative models for dexterous, single-view grasping of novel objects

This paper concerns the problem of how to learn to grasp dexterously, so...

Generating Quality Grasp Rectangle using Pix2Pix GAN for Intelligent Robot Grasping

Intelligent robot grasping is a very challenging task due to its inheren...

Robust and fast generation of top and side grasps for unknown objects

In this work, we present a geometry-based grasping algorithm that is cap...

A Billion Ways to Grasp: An Evaluation of Grasp Sampling Schemes on a Dense, Physics-based Grasp Data Set

Robot grasping is often formulated as a learning problem. With the incre...

Please sign up or login with your details

Forgot password? Click here to reset