Online prediction of robot to human handover events using vibrations

Harmeet Singh, Marco Controzzi, Christian Cipriani, Gaetano Di Caterina, Lykourgos Petropoulakis, John Soraghan

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

Abstract

One of the main issues for a robotic passer is to detect the onset of a handover, in order to avoid the object from being released when the human partner is not ready or if some impact occurs. This paper presents the methodology for a robotic passer, that is potentially able to estimate the interaction forces by the receiver on the object, thus to achieve fluent and safe handovers. The proposed system uses a vibrator that energizes the object and an accelerometer that monitors vibration propagation through the object during the handover. We focused on the machine-learning technique to classify between four states during object handover. A neural network was trained for these four states and tested online. In experimental trials an accuracy of 85.2% and 93.9% were obtained respectively for four classes and two classes of actions by a neural network classifier.
LanguageEnglish
Title of host publication2018 26th European Signal Processing Conference (EUSIPCO)
Place of PublicationPiscataway, NJ
PublisherIEEE
Pages687-691
Number of pages5
ISBN (Electronic)9789082797015
DOIs
Publication statusPublished - 3 Dec 2018
Event26th European Signal Processing Conference - Rome, Italy
Duration: 3 Sep 20187 Sep 2018
http://www.eusipco2018.org/index.php

Conference

Conference26th European Signal Processing Conference
Abbreviated titleEUSIPCO 2018
CountryItaly
CityRome
Period3/09/187/09/18
Internet address

Fingerprint

Robotics
Robots
Neural networks
Vibrators
Accelerometers
Learning systems
Classifiers

Keywords

  • autonomous
  • handover events
  • machine learning
  • neural networks

Cite this

Singh, H., Controzzi, M., Cipriani, C., Di Caterina, G., Petropoulakis, L., & Soraghan, J. (2018). Online prediction of robot to human handover events using vibrations. In 2018 26th European Signal Processing Conference (EUSIPCO) (pp. 687-691). Piscataway, NJ: IEEE. https://doi.org/10.23919/EUSIPCO.2018.8553474
Singh, Harmeet ; Controzzi, Marco ; Cipriani, Christian ; Di Caterina, Gaetano ; Petropoulakis, Lykourgos ; Soraghan, John. / Online prediction of robot to human handover events using vibrations. 2018 26th European Signal Processing Conference (EUSIPCO). Piscataway, NJ : IEEE, 2018. pp. 687-691
@inproceedings{179b94ded0824e30affeaf8fea33f92d,
title = "Online prediction of robot to human handover events using vibrations",
abstract = "One of the main issues for a robotic passer is to detect the onset of a handover, in order to avoid the object from being released when the human partner is not ready or if some impact occurs. This paper presents the methodology for a robotic passer, that is potentially able to estimate the interaction forces by the receiver on the object, thus to achieve fluent and safe handovers. The proposed system uses a vibrator that energizes the object and an accelerometer that monitors vibration propagation through the object during the handover. We focused on the machine-learning technique to classify between four states during object handover. A neural network was trained for these four states and tested online. In experimental trials an accuracy of 85.2{\%} and 93.9{\%} were obtained respectively for four classes and two classes of actions by a neural network classifier.",
keywords = "autonomous, handover events, machine learning, neural networks",
author = "Harmeet Singh and Marco Controzzi and Christian Cipriani and {Di Caterina}, Gaetano and Lykourgos Petropoulakis and John Soraghan",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2018",
month = "12",
day = "3",
doi = "10.23919/EUSIPCO.2018.8553474",
language = "English",
pages = "687--691",
booktitle = "2018 26th European Signal Processing Conference (EUSIPCO)",
publisher = "IEEE",

}

Singh, H, Controzzi, M, Cipriani, C, Di Caterina, G, Petropoulakis, L & Soraghan, J 2018, Online prediction of robot to human handover events using vibrations. in 2018 26th European Signal Processing Conference (EUSIPCO). IEEE, Piscataway, NJ, pp. 687-691, 26th European Signal Processing Conference, Rome, Italy, 3/09/18. https://doi.org/10.23919/EUSIPCO.2018.8553474

Online prediction of robot to human handover events using vibrations. / Singh, Harmeet; Controzzi, Marco; Cipriani, Christian; Di Caterina, Gaetano; Petropoulakis, Lykourgos; Soraghan, John.

2018 26th European Signal Processing Conference (EUSIPCO). Piscataway, NJ : IEEE, 2018. p. 687-691.

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

TY - GEN

T1 - Online prediction of robot to human handover events using vibrations

AU - Singh, Harmeet

AU - Controzzi, Marco

AU - Cipriani, Christian

AU - Di Caterina, Gaetano

AU - Petropoulakis, Lykourgos

AU - Soraghan, John

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/12/3

Y1 - 2018/12/3

N2 - One of the main issues for a robotic passer is to detect the onset of a handover, in order to avoid the object from being released when the human partner is not ready or if some impact occurs. This paper presents the methodology for a robotic passer, that is potentially able to estimate the interaction forces by the receiver on the object, thus to achieve fluent and safe handovers. The proposed system uses a vibrator that energizes the object and an accelerometer that monitors vibration propagation through the object during the handover. We focused on the machine-learning technique to classify between four states during object handover. A neural network was trained for these four states and tested online. In experimental trials an accuracy of 85.2% and 93.9% were obtained respectively for four classes and two classes of actions by a neural network classifier.

AB - One of the main issues for a robotic passer is to detect the onset of a handover, in order to avoid the object from being released when the human partner is not ready or if some impact occurs. This paper presents the methodology for a robotic passer, that is potentially able to estimate the interaction forces by the receiver on the object, thus to achieve fluent and safe handovers. The proposed system uses a vibrator that energizes the object and an accelerometer that monitors vibration propagation through the object during the handover. We focused on the machine-learning technique to classify between four states during object handover. A neural network was trained for these four states and tested online. In experimental trials an accuracy of 85.2% and 93.9% were obtained respectively for four classes and two classes of actions by a neural network classifier.

KW - autonomous

KW - handover events

KW - machine learning

KW - neural networks

UR - http://www.eusipco2018.org/

U2 - 10.23919/EUSIPCO.2018.8553474

DO - 10.23919/EUSIPCO.2018.8553474

M3 - Conference contribution book

SP - 687

EP - 691

BT - 2018 26th European Signal Processing Conference (EUSIPCO)

PB - IEEE

CY - Piscataway, NJ

ER -

Singh H, Controzzi M, Cipriani C, Di Caterina G, Petropoulakis L, Soraghan J. Online prediction of robot to human handover events using vibrations. In 2018 26th European Signal Processing Conference (EUSIPCO). Piscataway, NJ: IEEE. 2018. p. 687-691 https://doi.org/10.23919/EUSIPCO.2018.8553474