Adaptive Calibration of Soft Sensors Using Optimal Transportation Transfer Learning for Mass Production and Long‐Term Usage

Soft sensors suffer from high manufacturing tolerances and signal drift from long‐term usage, which degrades their practicality. Although deep learning has recently been proposed to address these issues, it is expensive in terms of data collection and processing. Therefore, an adaptive calibration method is proposed for soft sensors, suitable for mass production and long‐term usage. In addition to maintaining the original benefits of deep learning characterization, this method enables fast and accurate calibration by capturing the change in the characteristics of the sensor through domain adaptation, using optimal transportation. An offline calibration method is first described, which is for alleviating the difficulty in calibrating every single unit from mass produced soft sensors. The main advantage is that identically manufactured soft sensors in a large volume with variations can be calibrated with reduced time and effort for collecting and processing data. Online calibration is then discussed, which compensates for the parameter changes when a soft sensor is continuously used for an extended period of time. For a single sensor, even though the sensor shows signal drift from the long‐term usage, the calibrated network weights can be quickly adjusted online. Finally, the proposed adaptive calibration is experimentally evaluated using actual soft sensors.

[1]  Jim White,et al.  Polymer ageing: physics, chemistry or engineering? Time to reflect , 2006 .

[2]  Vincent Duchaine,et al.  Soft Tactile Skin Using an Embedded Ionic Liquid and Tomographic Imaging , 2015 .

[3]  Dongjun Lee,et al.  Wearable Finger Tracking and Cutaneous Haptic Interface with Soft Sensors for Multi-Fingered Virtual Manipulation , 2019, IEEE/ASME Transactions on Mechatronics.

[4]  Sungho Jo,et al.  Use of Deep Learning for Characterization of Microfluidic Soft Sensors , 2018, IEEE Robotics and Automation Letters.

[5]  Andrew G. Gillies,et al.  Nanowire active-matrix circuitry for low-voltage macroscale artificial skin. , 2010, Nature materials.

[6]  Taghi M. Khoshgoftaar,et al.  A survey of transfer learning , 2016, Journal of Big Data.

[7]  Mohammed Ismail,et al.  The Hysteresis Bouc-Wen Model, a Survey , 2009 .

[8]  Michelle C. Yuen,et al.  OmniSkins: Robotic skins that turn inanimate objects into multifunctional robots , 2018, Science Robotics.

[9]  Zeliang Liu,et al.  A Deep Material Network for Multiscale Topology Learning and Accelerated Nonlinear Modeling of Heterogeneous Materials , 2018, Computer Methods in Applied Mechanics and Engineering.

[10]  Lining Sun,et al.  A hysteresis compensation method of piezoelectric actuator: Model, identification and control , 2009 .

[11]  Sohee John Yoon,et al.  A Soft Optical Waveguide Coupled With Fiber Optics for Dynamic Pressure and Strain Sensing , 2018, IEEE Robotics and Automation Letters.

[12]  Yong-Lae Park,et al.  Direct printing of sub-30 μ m liquid metal patterns on three-dimensional surfaces for stretchable electronics , 2020, Journal of Micromechanics and Microengineering.

[13]  Antonio Bicchi,et al.  Toward soft robots you can depend on , 2008, IEEE Robotics & Automation Magazine.

[14]  Robert J. Wood,et al.  Soft robotic glove for combined assistance and at-home rehabilitation , 2015, Robotics Auton. Syst..

[15]  John S. Baras,et al.  Modeling and control of hysteresis in magnetostrictive actuators , 2004, Autom..

[16]  Robert J. Wood,et al.  Wearable soft sensing suit for human gait measurement , 2014, Int. J. Robotics Res..

[17]  Sungho Jo,et al.  Deep Full-Body Motion Network for a Soft Wearable Motion Sensing Suit , 2019, IEEE/ASME Transactions on Mechatronics.

[18]  Brian Byunghyun Kang,et al.  Exo-Glove: A Wearable Robot for the Hand with a Soft Tendon Routing System , 2015, IEEE Robotics & Automation Magazine.

[19]  J. Hutchinson,et al.  Physical aging of polymers , 1995 .

[20]  Carmel Majidi,et al.  Enhanced performance of microfluidic soft pressure sensors with embedded solid microspheres , 2016 .

[21]  Yong-Lae Park,et al.  Design and Fabrication of Soft Artificial Skin Using Embedded Microchannels and Liquid Conductors , 2012, IEEE Sensors Journal.

[22]  Yong-Lae Park,et al.  Optically Sensorized Elastomer Air Chamber for Proprioceptive Sensing of Soft Pneumatic Actuators , 2020, IEEE Robotics and Automation Letters.

[23]  Rebecca K. Kramer,et al.  Direct Writing of Gallium‐Indium Alloy for Stretchable Electronics , 2014 .

[24]  Steven Haker,et al.  Minimizing Flows for the Monge-Kantorovich Problem , 2003, SIAM J. Math. Anal..

[25]  Xiaoming Tao,et al.  Handbook of Smart Textiles , 2014 .

[26]  C. Su,et al.  An Analytical Generalized Prandtl–Ishlinskii Model Inversion for Hysteresis Compensation in Micropositioning Control , 2011, IEEE/ASME Transactions on Mechatronics.

[27]  Robert J. Wood,et al.  Biocompatible Soft Fluidic Strain and Force Sensors for Wearable Devices , 2018, Advanced functional materials.

[28]  Mariangela Manti,et al.  Stiffening in Soft Robotics: A Review of the State of the Art , 2016, IEEE Robotics & Automation Magazine.

[29]  Nicolas Courty,et al.  Joint distribution optimal transportation for domain adaptation , 2017, NIPS.

[30]  Yong-Lae Park,et al.  A Simple Tripod Mobile Robot Using Soft Membrane Vibration Actuators , 2019, IEEE Robotics and Automation Letters.

[31]  Robert J. Wood,et al.  Influence of cross-sectional geometry on the sensitivity and hysteresis of liquid-phase electronic pressure sensors , 2012 .

[32]  G. Whitesides,et al.  Eutectic Gallium‐Indium (EGaIn): A Liquid Metal Alloy for the Formation of Stable Structures in Microchannels at Room Temperature , 2008 .