Fiber optic tactile sensor for surface roughness recognition by machine learning algorithms

Abstract In this study, a sensor tip with a metallic hemispherical nozzle tip (MHNT) design based on the Fabry-Perot interferometer was developed for surface roughness recognition (SRR). Sandpaper samples with ten different arithmetical mean deviations of the surface (Sa) values were used as surfaces to be recognized. The feature vectors were found by applying the discrete wavelet transform (DWT) to the analog signals obtained from the sandpaper samples. Machine learning (ML) algorithms K-nearest neighbor (KNN) and support vector machine (SVM) were used for classification. An in-depth recognition process was carried out using the classifiers’ different length criteria and kernel types. In the test process, each category consists of two sub-categories as testing within the training dataset (TWITD) and testing without the training dataset (TWOTD). The experiments were carried out in a controlled manner with the conveyor belt system (CBS) and manual. As a result of the experimental studies, the average recognition rates (Rave) for CBS were found as 84.2% and 81.6% for TWITD and TWOTD, while the Rave for the manual are found as 80% and 77.5% for TWITD and TWOTD, respectively.

[1]  Fang Li,et al.  Diaphragm-Based Fiber Optic Fabry–Perot Accelerometer With High Consistency , 2014, Journal of Lightwave Technology.

[2]  Christian Cipriani,et al.  Roughness Encoding for Discrimination of Surfaces in Artificial Active-Touch , 2011, IEEE Transactions on Robotics.

[3]  J. Peters,et al.  Bioinspired tactile sensor for surface roughness discrimination , 2017 .

[4]  J. Schoenwald,et al.  A Novel Fiber Optic Tactile Array Sensor , 1987, Other Conferences.

[5]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[6]  S. Corbellini,et al.  Piezoresistive flexible composite for robotic tactile applications , 2014 .

[7]  M. Lalor,et al.  Frequency normalised wavelet transform for surface roughness analysis and characterisation , 2002 .

[8]  Yoji Yamada,et al.  Highly soft viscoelastic robot skin with a contact object-location-sensing capability , 2005, IEEE Transactions on Industrial Electronics.

[9]  Georgios Alexandros Skrimpas,et al.  Feature Extraction Using Discrete Wavelet Transform for Gear Fault Diagnosis of Wind Turbine Gearbox , 2016 .

[10]  Colin Bradley,et al.  A Fiber Optic Sensor for Surface Roughness Measurement , 1998 .

[11]  Vincenzo Niola,et al.  A problem of emphasizing features of a surface roughness by means the Discrete Wavelet Transform , 2005 .

[12]  Syed Jahangir Badashah,et al.  Image enhancement and surface roughness with feature extraction using DWT , 2011 .

[13]  Derek Abbott,et al.  Surface Roughness Detection of Arteries via Texture Analysis of Ultrasound Images for Early Diagnosis of Atherosclerosis , 2013, PloS one.

[14]  M. P. Givens.  Optical Properties of Metals , 1958 .

[15]  Jivko Sinapov,et al.  Vibrotactile Recognition and Categorization of Surfaces by a Humanoid Robot , 2011, IEEE Transactions on Robotics.

[16]  Ş. Hayber,et al.  A Simple, High Sensitive Fiber Optic Microphone Based on Cellulose Triacetate Diaphragm , 2018, Journal of Lightwave Technology.

[17]  Peter E. Hart,et al.  Nearest neighbor pattern classification , 1967, IEEE Trans. Inf. Theory.

[18]  D. Reynaerts,et al.  Characterisation of Tactile Sensors based on Fibre Bragg gratings Towards Temperature Independent Pressure Sensing , 2012 .

[19]  Deming Liu,et al.  Micromachined extrinsic Fabry-Pérot cavity for low-frequency acoustic wave sensing. , 2019, Optics express.

[20]  P.N. Brett,et al.  Distributive Tactile Sensing using Fibre Bragg Grating Sensors for Biomedical Applications , 2006, The First IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics, 2006. BioRob 2006..

[21]  Guy W. Mineau,et al.  A simple KNN algorithm for text categorization , 2001, Proceedings 2001 IEEE International Conference on Data Mining.

[22]  Gordon Cheng,et al.  In-hand object recognition via texture properties with robotic hands, artificial skin, and novel tactile descriptors , 2015, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids).

[23]  T. Martin McGinnity,et al.  Material recognition using tactile sensing , 2018, Expert Syst. Appl..

[24]  Hao Su,et al.  Real-time MRI-guided needle placement robot with integrated fiber optic force sensing , 2011, 2011 IEEE International Conference on Robotics and Automation.

[25]  Eric Maël,et al.  A sensor for dynamic tactile information with applications in human-robot interaction and object exploration , 2006, Robotics Auton. Syst..

[26]  K. R. Al-Balushi,et al.  Artificial neural networks and support vector machines with genetic algorithm for bearing fault detection , 2003 .

[27]  Mohammadreza Koopialipoor,et al.  Applying dual-tree complex discrete wavelet transform and gamma modulating function for simulation of ground motions , 2019, Engineering with Computers.

[28]  Mark H. Lee,et al.  A Survey of Robot Tactile Sensing Technology , 1989, Int. J. Robotics Res..

[29]  Abdulhamit Subasi,et al.  EEG signal classification using PCA, ICA, LDA and support vector machines , 2010, Expert Syst. Appl..

[30]  Michiko Nishiyama,et al.  A hemispheric hetero-core fiber optic tactile sensor for texture and hardness detection , 2016, SPIE OPTO.

[31]  Cosme Furlong,et al.  A Miniature MRI-Compatible Fiber-optic Force Sensor Utilizing Fabry-Perot Interferometer , 2011 .

[32]  C. Fragassa,et al.  Surface roughness evaluation in hardened materials by pattern recognition using network theory , 2018, International Journal on Interactive Design and Manufacturing (IJIDeM).

[33]  George Tzanetakis,et al.  Audio Analysis using the Discrete Wavelet Transform , 2001 .

[34]  Mamun Bin Ibne Reaz,et al.  Advances in Bio-Tactile Sensors for Minimally Invasive Surgery Using the Fibre Bragg Grating Force Sensor Technique:A Survey , 2014, Sensors.

[35]  Giulio Sandini,et al.  The iCub humanoid robot: an open platform for research in embodied cognition , 2008, PerMIS.

[36]  Denny Oetomo,et al.  Magnetic-based Soft Tactile Sensors with Deformable Continuous Force Transfer Medium for Resolving Contact Locations in Robotic Grasping and Manipulation , 2019, Sensors.

[37]  Longhui Qin,et al.  Roughness discrimination with bio-inspired tactile sensor manually sliding on polished surfaces , 2018 .

[38]  J. Heo,et al.  Tactile sensor arrays using fiber Bragg grating sensors , 2006 .

[39]  Eunsuk Choi,et al.  Biomimetic Tactile Sensors with Bilayer Fingerprint Ridges Demonstrating Texture Recognition , 2019, Micromachines.

[40]  Li Li,et al.  The effect of granularity on surface roughness and contact angle in wood sanding process , 2020 .

[41]  S. Gwo,et al.  Optical dielectric constants of single crystalline silver films in the long wavelength range , 2020 .

[42]  Daljeet Kaur Khanduja,et al.  Time Domain Signal Analysis Using Wavelet Packet Decomposition Approach , 2010, Int. J. Commun. Netw. Syst. Sci..

[43]  Giulio Sandini,et al.  Highly Sensitive Soft Tactile Sensors for an Anthropomorphic Robotic Hand , 2015, IEEE Sensors Journal.

[44]  Mark R. Cutkosky,et al.  Force Sensing Robot Fingers using Embedded Fiber Bragg Grating Sensors and Shape Deposition Manufacturing , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[45]  Wei-jun He.  Computational Neuroscience Applied in Surface Roughness Fiber Optic Sensor , 2019, Translational neuroscience.

[46]  Chunyang Wang,et al.  Discussion on method of optical surface roughness measurement , 2017, Other Conferences.

[47]  K. Yamazaki,et al.  A Reflective Fiber Optic Sensor for Surface Roughness In-Process Measurement , 2002 .

[48]  Giorgio Metta,et al.  Methods and Technologies for the Implementation of Large-Scale Robot Tactile Sensors , 2011, IEEE Transactions on Robotics.

[49]  Javad Dargahi,et al.  Design and analysis of tactile optical sensor for endovascular surgery , 2007, Photonics North.

[50]  Kaspar Althoefer,et al.  Fiber optics tactile array probe for tissue palpation during minimally invasive surgery , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[51]  George-Christopher Vosniakos,et al.  Predicting surface roughness in machining: a review , 2003 .

[52]  Frank Kirchner,et al.  Integration of Fiber-Optic Sensor Arrays into a Multi-Modal Tactile Sensor Processing System for Robotic End-Effectors , 2014, Sensors.

[53]  Wei Chen,et al.  Tactile Sensors for Friction Estimation and Incipient Slip Detection—Toward Dexterous Robotic Manipulation: A Review , 2018, IEEE Sensors Journal.

[54]  Hans J. Tiziani,et al.  Optical roughness measurements using extended white-light interferometry , 1999 .

[55]  Ashutosh Saxena,et al.  Reactive grasping using optical proximity sensors , 2009, 2009 IEEE International Conference on Robotics and Automation.

[56]  Russell H. Taylor,et al.  Miniature fiber-optic force sensor based on low-coherence Fabry-Pérot interferometry for vitreoretinal microsurgery , 2012, Biomedical optics express.

[57]  Zhengkun Yi,et al.  Enhanced surface roughness discrimination with optimized features from bio-inspired tactile sensor , 2017 .

[58]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..