SIA OpenIR  > 机器人学研究室
Hybrid Connectionist Symbolic Model for Morphologic Recognition by Tactile Sensing
He K(贺凯)1,2,3; Yu P(于鹏)1,2; Wang WX(王文学)1,2; Zhao L(赵亮)1,2; Yang T(杨铁)1,2; Elhaj, Imad H.5; Liu LQ(刘连庆)1,2
Department机器人学研究室
Source PublicationIEEE Sensors Journal
ISSN1530-437X
2021
Volume21Issue:5Pages:6497-6509
Indexed BySCI ; EI
EI Accession number20210709917558
WOS IDWOS:000616329300100
Contribution Rank1
Funding OrganizationNational Key Research and Development Program of China under Grant 2016YFE0206200 ; National Natural Science ofChina under Grant 61821005 and Grant 91748212 ; Natural Science Foundation of Liaoning Province of China under Grant 20180520035 ; Sichuan Science and Technology Program under Grant 2020YFSY0012
KeywordNetworked sensor fusion and decisions soft computing with sensor data sensor model analysis verification, smart sensor systems
Abstract

Morphology and texture detection, which are important components of tactile sensing, augment the response of human beings to external stimuli. Similarly, tactile sensing-based information acquisition systems in robots can help enhance the interactions of robots with the surroundings. The main drawback of morphology and texture sensing methods is their inability to explain and quantify sensing information, which makes it difficult to utilize prior knowledge and necessitates a new training process to fit the new task, even if the changes between the existing and new tasks are minuscule. Another drawback is its dependence on large datasets. To solve these problems, a hybrid connectionist symbolic model (HCSM) is proposed herein that combines historic symbolic knowledge and end-to-end neural networks. The symbolic model requires a smaller dataset and possesses an improved transferability of detection. Neural networks can be easily established and exhibit better fault tolerance for non-ideal samples. The HCSM model combines these advantages. Experiments with the tactile-based morphology and texture detection demonstrated that the new method can transfer the detection ability to fit new tasks without requiring additional retraining and has a 16% higher recognition precision than a convolutional neural network, LeNet, AlexNet, VGG16, and ResNet. The HCSM method with these features can broaden the range of applications of tactile sensing.

Language英语
WOS SubjectEngineering, Electrical & Electronic ; Instruments & Instrumentation ; Physics, Applied
WOS Research AreaEngineering ; Instruments & Instrumentation ; Physics
Funding ProjectNational Key Research and Development Program of China[2016YFE0206200] ; National Natural Science ofChina[61821005] ; National Natural Science ofChina[91748212] ; Natural Science Foundation of Liaoning Province of China[20180520035] ; Sichuan Science and Technology Program[2020YFSY0012]
Citation statistics
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/28336
Collection机器人学研究室
Corresponding AuthorLiu LQ(刘连庆)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Shenyang, China
2.Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences (CAS), Shenyang, China
3.University of the Chinese Academy of Sciences, Beijing 100049, China
4.Emerging Inst. of Technol. and the Department of Industrial and Manufacturing Systems Engineering, The University of Hong Kong, Hong Kong
5.Department of Electrical and Computer Engineering, The American University of Beirut, Beirut, Lebanon
Recommended Citation
GB/T 7714
He K,Yu P,Wang WX,et al. Hybrid Connectionist Symbolic Model for Morphologic Recognition by Tactile Sensing[J]. IEEE Sensors Journal,2021,21(5):6497-6509.
APA He K.,Yu P.,Wang WX.,Zhao L.,Yang T.,...&Liu LQ.(2021).Hybrid Connectionist Symbolic Model for Morphologic Recognition by Tactile Sensing.IEEE Sensors Journal,21(5),6497-6509.
MLA He K,et al."Hybrid Connectionist Symbolic Model for Morphologic Recognition by Tactile Sensing".IEEE Sensors Journal 21.5(2021):6497-6509.
Files in This Item:
File Name/Size DocType Version Access License
Hybrid Connectionist(6996KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He K(贺凯)]'s Articles
[Yu P(于鹏)]'s Articles
[Wang WX(王文学)]'s Articles
Baidu academic
Similar articles in Baidu academic
[He K(贺凯)]'s Articles
[Yu P(于鹏)]'s Articles
[Wang WX(王文学)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He K(贺凯)]'s Articles
[Yu P(于鹏)]'s Articles
[Wang WX(王文学)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Hybrid Connectionist Symbolic Model for Morphologic Recognition by Tactile Sensing.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.