Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)

<Previous Article In Volume
Next Article In Volume>

Improving the Efficiency of Object Grasp Detection on Embedded Platforms Using the AOGNet Neural Network Architecture

Authors
Clive A. A. Simpson1, *, Paul Gaynor1
1University of the West Indies, Mona, WI, Jamaica
*Corresponding author. Email: clivesimpson@myuwimona.edu.jm
Corresponding Author
Clive A. A. Simpson
Available Online 21 December 2023.
DOI
10.2991/978-94-6463-314-6_8How to use a DOI?
Keywords
And-Or Grammar Networks; Computer Vision; Neural Networks; Object Grasp Detection
Abstract

Robot grasp detection, commonly performed using Deep Neural Networks (DNNs), has proven to be a memory and power-intensive task that is required in resource-constrained environments. This paper proposes the use of And-Or-Grammar Networks (AOGNets) to reduce the constraints on embedded platforms. The experiments compare the accuracy, memory usage, space requirement, processing time, and power consumption of an AOGNet that is tuned to image recognition with implementations of Resnet, ResNeXt and Squeezenet on an Nvidia Jetson Nano. This paper also proposes using the AOGNet architecture for object grasp detection, as its performance on image classification tasks demonstrate that it is more tuned to the stringent operational requirements of embedded platforms.

Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

<Previous Article In Volume
Next Article In Volume>
Volume Title
Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)
Series
Atlantis Highlights in Computer Sciences
Publication Date
21 December 2023
ISBN
10.2991/978-94-6463-314-6_8
ISSN
2589-4900
DOI
10.2991/978-94-6463-314-6_8How to use a DOI?
Copyright
© 2023 The Author(s)
Open Access
Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Cite this article

risenwbib
TY  - CONF
AU  - Clive A. A. Simpson
AU  - Paul Gaynor
PY  - 2023
DA  - 2023/12/21
TI  - Improving the Efficiency of Object Grasp Detection on Embedded Platforms Using the AOGNet Neural Network Architecture
BT  - Proceedings of the International e-Conference on Advances in Computer Engineering and Communication Systems (ICACECS 2023)
PB  - Atlantis Press
SP  - 74
EP  - 84
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-314-6_8
DO  - 10.2991/978-94-6463-314-6_8
ID  - Simpson2023
ER  -