Online Morphological Adaptation for Tactile Sensing Augmentation

Sensor morphology and structure has the ability to significantly aid and improve tactile sensing capabilities, through mechanisms such as improved sensitivity or morphological computation. However, different tactile tasks require different morphologies posing a challenge as to how to best design sensors, and also how to enable sensor morphology to be varied. We introduce a jamming filter which, when placed over a tactile sensor, allows the filter to be shaped and molded online, thus varying the sensor structure. We demonstrate how this is beneficial for sensory tasks analyzing how the change in sensor structure varies the information that is gained using the sensor. Moreover, we show that appropriate morphology can significantly influence discrimination, and observe how the selection of an appropriate filter can increase the object classification accuracy when using standard classifiers by up to 28%.

[1]  Isabella Huang,et al.  A Depth Camera-Based Soft Fingertip Device for Contact Region Estimation and Perception-Action Coupling , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[2]  Richard A. Olshen,et al.  CART: Classification and Regression Trees , 1984 .

[3]  Heng Tao Shen,et al.  Principal Component Analysis , 2009, Encyclopedia of Biometrics.

[4]  Geoffrey E. Hinton,et al.  Neighbourhood Components Analysis , 2004, NIPS.

[5]  Makoto Shimojo,et al.  Mechanical filtering effect of elastic cover for tactile sensor , 1997, IEEE Trans. Robotics Autom..

[6]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[7]  Fumiya Iida,et al.  Active Sensing System with In Situ Adjustable Sensor Morphology , 2013, PloS one.

[8]  Fumiya Iida,et al.  Joint Entropy-Based Morphology Optimization of Soft Strain Sensor Networks for Functional Robustness , 2020, IEEE Sensors Journal.

[9]  Koji Shibuya,et al.  Theoretical Foundation for Design of Friction-Tunable Soft Finger With Wrinkle's Morphology , 2019, IEEE Robotics and Automation Letters.

[10]  R. Pfeifer,et al.  Cognition from the bottom up: on biological inspiration, body morphology, and soft materials , 2014, Trends in Cognitive Sciences.

[11]  Robert C. Hootman.  Manual on descriptive analysis testing for sensory evaluation , 1992 .

[12]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[13]  Kazumi Kobayashi,et al.  Relationship between the Structure of Human Finger Tissue and the Location of Tactile Receptors , 1998 .

[14]  Fumiya Iida,et al.  Tactile Sensing Applied to the Universal Gripper Using Conductive Thermoplastic Elastomer. , 2018, Soft robotics.

[15]  F. Iida,et al.  Adaptation of sensor morphology: an integrative view of perception from biologically inspired robotics perspective , 2016, Interface Focus.

[16]  Van Anh Ho,et al.  Wrinkled Soft Sensor With Variable Afferent Morphology: Case of Bending Actuation , 2020, IEEE Robotics and Automation Letters.

[17]  Fumiya Iida,et al.  Soft morphological processing of tactile stimuli for autonomous category formation , 2018, 2018 IEEE International Conference on Soft Robotics (RoboSoft).

[18]  Koji Shibuya,et al.  Wrin’Tac: Tactile Sensing System With Wrinkle's Morphological Change , 2017, IEEE Transactions on Industrial Informatics.

[19]  Christopher D. Manning,et al.  Introduction to Information Retrieval , 2010, J. Assoc. Inf. Sci. Technol..

[20]  Fumiya Iida,et al.  Localized differential sensing of soft deformable surfaces , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[21]  F. Iida,et al.  Action Augmentation of Tactile Perception for Soft-Body Palpation , 2021, Soft robotics.

[22]  Aude Billard,et al.  Morphology and Learning - A Case Study on Whiskers , 2004 .

[23]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[24]  Giorgio Metta,et al.  A Flexible and Robust Large Scale Capacitive Tactile System for Robots , 2013, IEEE Sensors Journal.

[25]  B Mazzolai,et al.  Soft robotic arm inspired by the octopus: I. From biological functions to artificial requirements , 2012, Bioinspiration & biomimetics.

[26]  Heinrich M. Jaeger,et al.  Universal robotic gripper based on the jamming of granular material , 2010, Proceedings of the National Academy of Sciences.

[27]  Ethem Alpaydin,et al.  Support Vector Machines for Multi-class Classification , 1999, IWANN.

[28]  Van Anh Ho,et al.  Wrinkled Soft Sensor With Variable Afferent Morphology , 2019, IEEE Robotics and Automation Letters.

[29]  Hiroyuki Fujita,et al.  Liquid-based tactile sensing array with adjustable sensing range and sensitivity by using dielectric liquid , 2015 .

[30]  H. Abdi,et al.  Principal component analysis , 2010 .

[31]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[32]  Yan Qi-sheng,et al.  SVM with RBF kernel and its application research , 2006 .

[33]  Van Anh Ho,et al.  Morphological computation in haptic sensation and interaction: from nature to robotics , 2018, Adv. Robotics.

[34]  Jonathan Rossiter,et al.  WormTIP: An Invertebrate Inspired Active Tactile Imaging Pneumostat , 2015, Living Machines.

[35]  R. Johansson,et al.  Properties of cutaneous mechanoreceptors in the human hand related to touch sensation. , 1984, Human neurobiology.

[36]  Fumiya Iida,et al.  Efficient Bayesian Exploration for Soft Morphology-Action Co-optimization , 2020, 2020 3rd IEEE International Conference on Soft Robotics (RoboSoft).

[37]  Fumiya Iida,et al.  Structuring of tactile sensory information for category formation in robotics palpation , 2020, Autonomous Robots.