Force/torque sensor calibration method by using deep-learning

The force/torque sensor is an important tool that gives a robot an ability to interact with their usage 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 requ...

Full description

Saved in:
Bibliographic Details
Published in2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI) pp. 777 - 782
Main Authors Hyun Seok Oh, Gitae Kang, Uikyum Kim, Joon Kyue Seo, Won Suk You, Hyouk Ryeol Choi
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.06.2017
Subjects
Calibration
Coupling Effect
Couplings
Deep Learning
Deep Neural Network
Force
Force/Torque
Robot sensing systems
Sensors
Torque
Training data
Online AccessGet full text

Cover

More Information
Summary:The force/torque sensor is an important tool that gives a robot an ability to interact with their usage 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 also explain some tricks for learning, and then verify the calibration results through several experiments.
DOI:10.1109/URAI.2017.7992824