Calibration of 6 axis force/torque sensor by using deep-learning method

Hyun Seok Oh; Gitae Kang; Uikyum Kim; Joon Kyue Seo; Hyouk Ryeol Choi

doi:10.1109/COASE.2017.8256282

Calibration of 6 axis force/torque sensor by using deep-learning method

Hyun Seok Oh
, Gitae Kang
, Uikyum Kim
, Joon Kyue Seo
, Hyouk Ryeol Choi

Department of Mechanical Engineering

Sungkyunkwan University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

The force/torque sensor is a important tool that gives a robot an ability to interact with environments. Calibration is essential for these force/torque sensors to convert the raw sensor values to accurate forces and torques. However, in practice, the multi-axis force/torque sensor requires complex multi-step data processing, because of the coupling effects and nonlinearity of sensors. Moreover, accuracy is not guaranteed. To solve this problem, we propose an accurate force/torque sensor calibration method that can calibrate the sensor in single step by using deep-learning algorithm, and introduce the method for modeling the DNN(deep neural network) used in this calibration process. In addition, we verify the calibration results through several experiments.

Original language	English
Title of host publication	2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017
Publisher	IEEE Computer Society
Pages	1316-1317
Number of pages	2
ISBN (Electronic)	9781509067800
DOIs	https://doi.org/10.1109/COASE.2017.8256282
State	Published - 1 Jul 2017
Event	13th IEEE Conference on Automation Science and Engineering, CASE 2017 - Xi'an, China Duration: 20 Aug 2017 → 23 Aug 2017

Publication series

Name	IEEE International Conference on Automation Science and Engineering
Volume	2017-August
ISSN (Print)	2161-8070
ISSN (Electronic)	2161-8089

Conference

Conference	13th IEEE Conference on Automation Science and Engineering, CASE 2017
Country/Territory	China
City	Xi'an
Period	20/08/17 → 23/08/17

Access to Document

10.1109/COASE.2017.8256282

Cite this

Oh, H. S., Kang, G., Kim, U., Seo, J. K., & Choi, H. R. (2017). Calibration of 6 axis force/torque sensor by using deep-learning method. In 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017 (pp. 1316-1317). (IEEE International Conference on Automation Science and Engineering; Vol. 2017-August). IEEE Computer Society. https://doi.org/10.1109/COASE.2017.8256282

@inproceedings{a59425dfcb8c446bac27e73532a2b5b9,

title = "Calibration of 6 axis force/torque sensor by using deep-learning method",

abstract = "The force/torque sensor is a important tool that gives a robot an ability to interact with environments. Calibration is essential for these force/torque sensors to convert the raw sensor values to accurate forces and torques. However, in practice, the multi-axis force/torque sensor requires complex multi-step data processing, because of the coupling effects and nonlinearity of sensors. Moreover, accuracy is not guaranteed. To solve this problem, we propose an accurate force/torque sensor calibration method that can calibrate the sensor in single step by using deep-learning algorithm, and introduce the method for modeling the DNN(deep neural network) used in this calibration process. In addition, we verify the calibration results through several experiments.",

author = "Oh, \{Hyun Seok\} and Gitae Kang and Uikyum Kim and Seo, \{Joon Kyue\} and Choi, \{Hyouk Ryeol\}",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 13th IEEE Conference on Automation Science and Engineering, CASE 2017 ; Conference date: 20-08-2017 Through 23-08-2017",

year = "2017",

month = jul,

day = "1",

doi = "10.1109/COASE.2017.8256282",

language = "English",

series = "IEEE International Conference on Automation Science and Engineering",

publisher = "IEEE Computer Society",

pages = "1316--1317",

booktitle = "2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017",

}

Oh, HS, Kang, G, Kim, U, Seo, JK & Choi, HR 2017, Calibration of 6 axis force/torque sensor by using deep-learning method. in 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017. IEEE International Conference on Automation Science and Engineering, vol. 2017-August, IEEE Computer Society, pp. 1316-1317, 13th IEEE Conference on Automation Science and Engineering, CASE 2017, Xi'an, China, 20/08/17. https://doi.org/10.1109/COASE.2017.8256282

Calibration of 6 axis force/torque sensor by using deep-learning method. / Oh, Hyun Seok; Kang, Gitae; Kim, Uikyum et al.
2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017. IEEE Computer Society, 2017. p. 1316-1317 (IEEE International Conference on Automation Science and Engineering; Vol. 2017-August).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Calibration of 6 axis force/torque sensor by using deep-learning method

AU - Oh, Hyun Seok

AU - Kang, Gitae

AU - Kim, Uikyum

AU - Seo, Joon Kyue

AU - Choi, Hyouk Ryeol

PY - 2017/7/1

Y1 - 2017/7/1

N2 - The force/torque sensor is a important tool that gives a robot an ability to interact with environments. Calibration is essential for these force/torque sensors to convert the raw sensor values to accurate forces and torques. However, in practice, the multi-axis force/torque sensor requires complex multi-step data processing, because of the coupling effects and nonlinearity of sensors. Moreover, accuracy is not guaranteed. To solve this problem, we propose an accurate force/torque sensor calibration method that can calibrate the sensor in single step by using deep-learning algorithm, and introduce the method for modeling the DNN(deep neural network) used in this calibration process. In addition, we verify the calibration results through several experiments.

AB - The force/torque sensor is a important tool that gives a robot an ability to interact with environments. Calibration is essential for these force/torque sensors to convert the raw sensor values to accurate forces and torques. However, in practice, the multi-axis force/torque sensor requires complex multi-step data processing, because of the coupling effects and nonlinearity of sensors. Moreover, accuracy is not guaranteed. To solve this problem, we propose an accurate force/torque sensor calibration method that can calibrate the sensor in single step by using deep-learning algorithm, and introduce the method for modeling the DNN(deep neural network) used in this calibration process. In addition, we verify the calibration results through several experiments.

UR - https://www.scopus.com/pages/publications/85044955930

U2 - 10.1109/COASE.2017.8256282

DO - 10.1109/COASE.2017.8256282

M3 - Conference contribution

AN - SCOPUS:85044955930

T3 - IEEE International Conference on Automation Science and Engineering

SP - 1316

EP - 1317

BT - 2017 13th IEEE Conference on Automation Science and Engineering, CASE 2017

PB - IEEE Computer Society

T2 - 13th IEEE Conference on Automation Science and Engineering, CASE 2017

Y2 - 20 August 2017 through 23 August 2017

ER -

Calibration of 6 axis force/torque sensor by using deep-learning method

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this