This paper deals with the design, fabrication and preliminary experimental results of a novel soft tactile sensing system for large surfaces, aiming at detecting the location of the contact points on the surface of the sensor. The sensor is composed by soft material with an IMU embedded on a deformable silicon-based surface. Using the data provided from the IMU during morphological variations of the soft sensor, the aim of the sensing system is to recognize different locations of single contact points and linear regions of contact points resembling the contacts with soft linear objects. In order to achieve this behaviour, an artificial neural network has been used, and evaluated trough experiments. The reported results show that the sensing system is able to discriminate between a grid of single contact locations, and among different linear regions of contact points, with a mean accuracy superior than 80%, and peak accuracy of 97.97% (for the single single point contact locations) and 97.54% (for the linear regions of contact points.)

A Low Cost Tactile Sensor for Large Surfaces Based on Deformable Skin with Embedded IMU

Roberto Meattini;Davide Chiaravalli;Gianluca Palli;Claudio Melchiorri
2020

Abstract

This paper deals with the design, fabrication and preliminary experimental results of a novel soft tactile sensing system for large surfaces, aiming at detecting the location of the contact points on the surface of the sensor. The sensor is composed by soft material with an IMU embedded on a deformable silicon-based surface. Using the data provided from the IMU during morphological variations of the soft sensor, the aim of the sensing system is to recognize different locations of single contact points and linear regions of contact points resembling the contacts with soft linear objects. In order to achieve this behaviour, an artificial neural network has been used, and evaluated trough experiments. The reported results show that the sensing system is able to discriminate between a grid of single contact locations, and among different linear regions of contact points, with a mean accuracy superior than 80%, and peak accuracy of 97.97% (for the single single point contact locations) and 97.54% (for the linear regions of contact points.)
Proceedings. 2020 IEEE Conference on IndustrialCyberphysical Systems (ICPS)
501
506
Yuki Iwamoto, Roberto Meattini, Davide Chiaravalli, Gianluca Palli, Koji Shibuya, Claudio Melchiorri
File in questo prodotto:
File Dimensione Formato  
yuki_paper_OA_remodel.pdf

embargo fino al 04/06/2021

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 2.72 MB
Formato Adobe PDF
2.72 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/11585/785153
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact