Intelligent Tennis Robot Based on a Deep Neural Network

Gu, S; Zeng, W; Jia, Y; Yan, Z

Intelligent Tennis Robot Based on a Deep Neural Network

Gu, S Zeng, W Jia, Y Yan, Z

Permalink

Publisher:: MDPI AG
Publication Type:: Journal Article
Citation:: Applied Sciences, 9, (18), pp. 3746-3746

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Published versionAdobe PDF (6.34 MB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Gu, S
dc.contributor.author	Zeng, W
dc.contributor.author	Jia, Y
dc.contributor.author	Yan, Z https://orcid.org/0000-0003-3368-2100
dc.date.accessioned	2020-06-04T01:45:55Z
dc.date.available	2020-06-04T01:45:55Z
dc.identifier.citation	Applied Sciences, 9, (18), pp. 3746-3746
dc.identifier.issn	2076-3417
dc.identifier.uri	http://hdl.handle.net/10453/141091
dc.description.abstract	<jats:p>In this paper, an improved you only look once (YOLOv3) algorithm is proposed to make the detection effect better and improve the performance of a tennis ball detection robot. The depth-separable convolution network is combined with the original YOLOv3 and the residual block is added to extract the features of the object. The feature map output by the residual block is merged with the target detection layer through the shortcut layer to improve the network structure of YOLOv3. Both the original model and the improved model are trained by the same tennis ball data set. The results show that the recall is improved from 67.70% to 75.41% and the precision is 88.33%, which outperforms the original 77.18%. The recognition speed of the model is increased by half and the weight is reduced by half after training. All these features provide a great convenience for the application of the deep neural network in embedded devices. Our goal is that the robot is capable of picking up more tennis balls as soon as possible. Inspired by the maximum clique problem (MCP), the pointer network (Ptr-Net) and backtracking algorithm (BA) are utilized to make the robot find the place with the highest concentration of tennis balls. According to the training results, when the number of tennis balls is less than 45, the accuracy of determining the concentration of tennis balls can be as high as 80%.</jats:p>
dc.language	en
dc.publisher	MDPI AG
dc.relation.ispartof	Applied Sciences
dc.relation.isbasedon	10.3390/app9183746
dc.rights	info:eu-repo/semantics/openAccess
dc.title	Intelligent Tennis Robot Based on a Deep Neural Network
dc.type	Journal Article
utslib.citation.volume	9
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney
utslib.copyright.status	open_access	*
dc.date.updated	2020-06-04T01:45:48Z
pubs.issue	18
pubs.publication-status	Published online
pubs.volume	9
utslib.start-page	3746
utslib.citation.issue	18

Abstract:

In this paper, an improved you only look once (YOLOv3) algorithm is proposed to make the detection effect better and improve the performance of a tennis ball detection robot. The depth-separable convolution network is combined with the original YOLOv3 and the residual block is added to extract the features of the object. The feature map output by the residual block is merged with the target detection layer through the shortcut layer to improve the network structure of YOLOv3. Both the original model and the improved model are trained by the same tennis ball data set. The results show that the recall is improved from 67.70% to 75.41% and the precision is 88.33%, which outperforms the original 77.18%. The recognition speed of the model is increased by half and the weight is reduced by half after training. All these features provide a great convenience for the application of the deep neural network in embedded devices. Our goal is that the robot is capable of picking up more tennis balls as soon as possible. Inspired by the maximum clique problem (MCP), the pointer network (Ptr-Net) and backtracking algorithm (BA) are utilized to make the robot find the place with the highest concentration of tennis balls. According to the training results, when the number of tennis balls is less than 45, the accuracy of determining the concentration of tennis balls can be as high as 80%.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/141091