Multi-Axial Force/Torque Sensor Calibration Method Based on Deep-Learning

The multi-axial force/torque sensor for advanced robotic applications utilizes the internal strain of deformable structure for its measurement. Thus, there exist coupling and errors due to nonlinearity caused from the variation of the electric signal with respect to the strain. This paper presents a method of calibrating six-axis force/torque sensors with high accuracy based on deep learning. The method can solve the aforementioned problems easily by using deep-neural network (DNN). After performing the structural analysis of the sensor, generalized equations of the electric signal is derived, which leads it to the basic DNN structure, and optimization is performed. Training and test data are prepared by using a dummy and a reference sensor. Then, the proposed method is validated by comparing the three results obtained from the linear transformation method based on least-square method, two-step neural-network, and the DNN-based method for each untrained test data set.

[1]  Jeff Heaton,et al.  Introduction to Neural Networks for C#, 2nd Edition , 2008 .

[2]  Kaspar Althoefer,et al.  Multi-Axis Force/Torque Sensor Based on Simply-Supported Beam and Optoelectronics , 2016, Sensors.

[3]  Hong Liu,et al.  DLR-Hand II: next generation of a dextrous robot hand , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[4]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[5]  Jung-Hoon Kim,et al.  Shape optimization of a mechanically decoupled six-axis force/torque sensor , 2014 .

[6]  Clément Gosselin,et al.  Modeling of physical human–robot interaction , 2016 .

[7]  Aiguo Song,et al.  Fast Estimation of Strains for Cross-Beams Six-Axis Force/Torque Sensors by Mechanical Modeling , 2013, Sensors.

[8]  Tien-Fu Lu,et al.  Neural-network-based 3D force/torque sensor calibration for robot applications , 1997 .

[9]  Darwin G. Caldwell,et al.  Design of the Hydraulically Actuated, Torque-Controlled Quadruped Robot HyQ2Max , 2017, IEEE/ASME Transactions on Mechatronics.

[10]  Yong Yu,et al.  A research of multi-axis force sensor static decoupling method based on neural network , 2009, 2009 IEEE International Conference on Automation and Logistics.

[11]  Aiguo Song,et al.  A Robust Static Decoupling Algorithm for 3-Axis Force Sensors Based on Coupling Error Model and ε-SVR , 2012, Sensors.

[12]  Dan Zhang,et al.  Design and fabrication of a six-dimensional wrist force/torque sensor based on E-type membranes compared to cross beams , 2010 .

[13]  Ahmad Kalhor,et al.  On human–robot interaction of a 3-DOF decoupled parallel mechanism based on the design and construction of a novel and low-cost 3-DOF force sensor , 2017 .

[14]  Blake Hannaford,et al.  Force Sensor Integrated Surgical Forceps for Minimally Invasive Robotic Surgery , 2015, IEEE Transactions on Robotics.

[15]  Hyouk Ryeol Choi,et al.  A Novel Six-Axis Force/Torque Sensor for Robotic Applications , 2017, IEEE/ASME Transactions on Mechatronics.

[16]  Zhenyuan Jia,et al.  A novel parallel piezoelectric six-axis heavy force/torque sensor , 2009 .

[17]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[18]  Hyouk Ryeol Choi,et al.  A Surgical Palpation Probe With 6-Axis Force/Torque Sensing Capability for Minimally Invasive Surgery , 2018, IEEE Transactions on Industrial Electronics.

[19]  Jeff Heaton,et al.  Introduction to neural networks for C , 2008 .

[20]  Aiguo Song,et al.  A novel self-decoupled four degree-of-freedom wrist force/torque sensor , 2007 .

[21]  Alessandro De Luca,et al.  Collision Detection and Safe Reaction with the DLR-III Lightweight Manipulator Arm , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Hosang Jung,et al.  A Capacitive-Type Novel Six-Axis Force/Torque Sensor for Robotic Applications , 2016, IEEE Sensors Journal.

[23]  Yong Hu,et al.  Nonlinear static decoupling of six-dimension force sensor for walker dynamometer system based on artificial neural network , 2009, 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[24]  Hyoukryeol Choi,et al.  Force/torque sensor calibration method by using deep-learning , 2017, 2017 14th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI).