Recognition of contact state of four layers arrayed type tactile sensor by using neural network

Seiji Aoyagi, Takaaki Tanaka, Mamoru Minami

Research output: Chapter in Book/Report/Conference proceedingConference contribution

8 Citations (Scopus)

Abstract

Imitating human finger tip, an arrayed type tactile sensor comprising four layers is under development. In this report, a recognizing method of force and its direction is proposed by using two stage neural networks, and its validity is investigated by simulation. The procedure of simulation is as follows: first, the stress distribution of this sensor sheet applied force is simulated by FEM (Finite Element Method). The obtained stress data are assigned to each assumed stress sensing element of the array. Second, all data of these elements are processed by the first stage neural network, and force direction is calculated. Third, using this direction data and maximal stress data of 4 layers are processed by the second stage neural network.

Original languageEnglish
Title of host publicationProceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition
Pages393-397
Number of pages5
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event2006 IEEE International Conference on Information Acquisition, ICIA 2006 - Weihai, Shandong, China
Duration: Aug 20 2006Aug 23 2006

Other

Other2006 IEEE International Conference on Information Acquisition, ICIA 2006
CountryChina
CityWeihai, Shandong
Period8/20/068/23/06

Fingerprint

Neural networks
Sensors
Stress concentration
Finite element method
Sensor
Simulation
Underdevelopment

ASJC Scopus subject areas

  • Information Systems
  • Information Systems and Management
  • Control and Systems Engineering

Cite this

Aoyagi, S., Tanaka, T., & Minami, M. (2006). Recognition of contact state of four layers arrayed type tactile sensor by using neural network. In Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition (pp. 393-397). [4097966] https://doi.org/10.1109/ICIA.2006.305744

Recognition of contact state of four layers arrayed type tactile sensor by using neural network. / Aoyagi, Seiji; Tanaka, Takaaki; Minami, Mamoru.

Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition. 2006. p. 393-397 4097966.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Aoyagi, S, Tanaka, T & Minami, M 2006, Recognition of contact state of four layers arrayed type tactile sensor by using neural network. in Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition., 4097966, pp. 393-397, 2006 IEEE International Conference on Information Acquisition, ICIA 2006, Weihai, Shandong, China, 8/20/06. https://doi.org/10.1109/ICIA.2006.305744
Aoyagi S, Tanaka T, Minami M. Recognition of contact state of four layers arrayed type tactile sensor by using neural network. In Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition. 2006. p. 393-397. 4097966 https://doi.org/10.1109/ICIA.2006.305744
Aoyagi, Seiji ; Tanaka, Takaaki ; Minami, Mamoru. / Recognition of contact state of four layers arrayed type tactile sensor by using neural network. Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition. 2006. pp. 393-397
@inproceedings{f65575cb7113430281ca7efb7cb53e21,
title = "Recognition of contact state of four layers arrayed type tactile sensor by using neural network",
abstract = "Imitating human finger tip, an arrayed type tactile sensor comprising four layers is under development. In this report, a recognizing method of force and its direction is proposed by using two stage neural networks, and its validity is investigated by simulation. The procedure of simulation is as follows: first, the stress distribution of this sensor sheet applied force is simulated by FEM (Finite Element Method). The obtained stress data are assigned to each assumed stress sensing element of the array. Second, all data of these elements are processed by the first stage neural network, and force direction is calculated. Third, using this direction data and maximal stress data of 4 layers are processed by the second stage neural network.",
author = "Seiji Aoyagi and Takaaki Tanaka and Mamoru Minami",
year = "2006",
doi = "10.1109/ICIA.2006.305744",
language = "English",
pages = "393--397",
booktitle = "Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition",

}

TY - GEN

T1 - Recognition of contact state of four layers arrayed type tactile sensor by using neural network

AU - Aoyagi, Seiji

AU - Tanaka, Takaaki

AU - Minami, Mamoru

PY - 2006

Y1 - 2006

N2 - Imitating human finger tip, an arrayed type tactile sensor comprising four layers is under development. In this report, a recognizing method of force and its direction is proposed by using two stage neural networks, and its validity is investigated by simulation. The procedure of simulation is as follows: first, the stress distribution of this sensor sheet applied force is simulated by FEM (Finite Element Method). The obtained stress data are assigned to each assumed stress sensing element of the array. Second, all data of these elements are processed by the first stage neural network, and force direction is calculated. Third, using this direction data and maximal stress data of 4 layers are processed by the second stage neural network.

AB - Imitating human finger tip, an arrayed type tactile sensor comprising four layers is under development. In this report, a recognizing method of force and its direction is proposed by using two stage neural networks, and its validity is investigated by simulation. The procedure of simulation is as follows: first, the stress distribution of this sensor sheet applied force is simulated by FEM (Finite Element Method). The obtained stress data are assigned to each assumed stress sensing element of the array. Second, all data of these elements are processed by the first stage neural network, and force direction is calculated. Third, using this direction data and maximal stress data of 4 layers are processed by the second stage neural network.

UR - http://www.scopus.com/inward/record.url?scp=46249100362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46249100362&partnerID=8YFLogxK

U2 - 10.1109/ICIA.2006.305744

DO - 10.1109/ICIA.2006.305744

M3 - Conference contribution

SP - 393

EP - 397

BT - Proceedings of IEEE ICIA 2006 - 2006 IEEE International Conference on Information Acquisition

ER -