Online prediction of robot to human handover events using vibrations

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

doi:10.23919/EUSIPCO.2018.8553474

Online prediction of robot to human handover events using vibrations

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

Electronic And Electrical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

2 Citations (Scopus)

34 Downloads (Pure)

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.

Original language	English
Title of host publication	2018 26th European Signal Processing Conference (EUSIPCO)
Place of Publication	Piscataway, NJ
Publisher	IEEE
Pages	687-691
Number of pages	5
ISBN (Electronic)	9789082797015
DOIs	https://doi.org/10.23919/EUSIPCO.2018.8553474
Publication status	Published - 3 Dec 2018
Event	26th European Signal Processing Conference - Rome, Italy Duration: 3 Sept 2018 → 7 Sept 2018 http://www.eusipco2018.org/index.php

Conference

Conference	26th European Signal Processing Conference
Abbreviated title	EUSIPCO 2018
Country/Territory	Italy
City	Rome
Period	3/09/18 → 7/09/18
Internet address	http://www.eusipco2018.org/index.php

Keywords

autonomous
handover events
machine learning
neural networks

Access to Document

10.23919/EUSIPCO.2018.8553474

Singh-etal-EUSIPCO-2018-Online-prediction-of-robot-to-human-handoverAccepted author manuscript, 914 KB

Cite this

@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 = "{\textcopyright} 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.; 26th European Signal Processing Conference, EUSIPCO 2018 ; Conference date: 03-09-2018 Through 07-09-2018",

year = "2018",

month = dec,

day = "3",

doi = "10.23919/EUSIPCO.2018.8553474",

language = "English",

pages = "687--691",

booktitle = "2018 26th European Signal Processing Conference (EUSIPCO)",

publisher = "IEEE",

url = "http://www.eusipco2018.org/index.php",

}

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

T2 - 26th European Signal Processing Conference

Y2 - 3 September 2018 through 7 September 2018

ER -

Online prediction of robot to human handover events using vibrations

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this