University of Surrey

Test tubes in the lab Research in the ATI Dance Research

From Vision to Grasping: Adapting Visual Networks

Allday, Rebecca, Hadfield, Simon and Bowden, Richard (2017) From Vision to Grasping: Adapting Visual Networks In: TAROS-2017, 2017-07-19 - 2017-07-21, Guildford, UK.

[img]
Preview
Text
main.pdf - Accepted version Manuscript
Available under License : See the attached licence file.

Download (306kB) | Preview
[img]
Preview
PDF (licence)
SRI_deposit_agreement.pdf
Available under License : See the attached licence file.

Download (33kB) | Preview

Abstract

Grasping is one of the oldest problems in robotics and is still considered challenging, especially when grasping unknown objects with unknown 3D shape. We focus on exploiting recent advances in computer vision recognition systems. Object classification problems tend to have much larger datasets to train from and have far fewer practical constraints around the size of the model and speed to train. In this paper we will investigate how to adapt Convolutional Neural Networks (CNNs), traditionally used for image classification, for planar robotic grasping. We consider the differences in the problems and how a network can be adjusted to account for this. Positional information is far more important to robotics than generic image classification tasks, where max pooling layers are used to improve translation invariance. By using a more appropriate network structure we are able to obtain improved accuracy while simultaneously improving run times and reducing memory consumption by reducing model size by up to 69%.

Item Type: Conference or Workshop Item (Conference Poster)
Subjects : Electronic Engineering
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Allday, Rebeccar.allday@surrey.ac.ukUNSPECIFIED
Hadfield, Simons.hadfield@surrey.ac.ukUNSPECIFIED
Bowden, RichardR.Bowden@surrey.ac.ukUNSPECIFIED
Date : 2017
Copyright Disclaimer : The final publication is available at Springer via http://www.springer.com/series/1244
Contributors :
ContributionNameEmailORCID
UNSPECIFIEDSpringer, UNSPECIFIEDUNSPECIFIED
Uncontrolled Keywords : Robotic Grasping, Machine Learning, CNNs, SqueezeNet, AlexNet
Depositing User : Symplectic Elements
Date Deposited : 05 May 2017 13:48
Last Modified : 25 Jul 2017 14:28
URI: http://epubs.surrey.ac.uk/id/eprint/814114

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800