Towards Robot-Human Reliable Hand-over: Continuous Detection of Object Perturbation Force Direction

Augusto Gomez, Ignacio Rano, SA Coleman, T.Martin McGinnity

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

Abstract

A fundamental aspect of many human-robot col- laborative tasks is object exchange or handover. Several tech- niques have been proposed to decide when a robot hand or gripper should release an object for a human to receive. However, these techniques typically neglect the reliability of the handover, assuming the process will occur without issue. Based on the fact that humans apply pulling forces in specific directions when receiving an object, this paper presents a recursive procedure enabling a robot to release an object appropriately and timely during a handover. Experiments with naive users showed subject-specific consistent pulling directions during robot-human handovers, highlighting the need for a system to be capable of detecting force directions in relation to objects. The approach reported in this paper shows that through tactile sensing the proposed approach can accurately classify between five different actions impacting an object held by a robot hand. The recursive nature of the system also enables detection of sequences of different actions, enabling the robot to decide to safely release the object only when the pulling performed by the human is in the right direction.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages7
Publication statusAccepted/In press - 30 May 2017
EventIEEE International Symposium on Robot and Human Interactive Communication - Lisbon, Portugal
Duration: 30 May 2017 → …

Conference

ConferenceIEEE International Symposium on Robot and Human Interactive Communication
Period30/05/17 → …

Fingerprint

End effectors
Robots
Grippers
Experiments

Keywords

  • hand-overs
  • grasping
  • robotics

Cite this

@inproceedings{6cd1ea7c92e54afb94562f7127c66ffd,
title = "Towards Robot-Human Reliable Hand-over: Continuous Detection of Object Perturbation Force Direction",
abstract = "A fundamental aspect of many human-robot col- laborative tasks is object exchange or handover. Several tech- niques have been proposed to decide when a robot hand or gripper should release an object for a human to receive. However, these techniques typically neglect the reliability of the handover, assuming the process will occur without issue. Based on the fact that humans apply pulling forces in specific directions when receiving an object, this paper presents a recursive procedure enabling a robot to release an object appropriately and timely during a handover. Experiments with naive users showed subject-specific consistent pulling directions during robot-human handovers, highlighting the need for a system to be capable of detecting force directions in relation to objects. The approach reported in this paper shows that through tactile sensing the proposed approach can accurately classify between five different actions impacting an object held by a robot hand. The recursive nature of the system also enables detection of sequences of different actions, enabling the robot to decide to safely release the object only when the pulling performed by the human is in the right direction.",
keywords = "hand-overs, grasping, robotics",
author = "Augusto Gomez and Ignacio Rano and SA Coleman and T.Martin McGinnity",
year = "2017",
month = "5",
day = "30",
language = "English",
booktitle = "Unknown Host Publication",

}

Gomez, A, Rano, I, Coleman, SA & McGinnity, TM 2017, Towards Robot-Human Reliable Hand-over: Continuous Detection of Object Perturbation Force Direction. in Unknown Host Publication. IEEE International Symposium on Robot and Human Interactive Communication, 30/05/17.

Towards Robot-Human Reliable Hand-over: Continuous Detection of Object Perturbation Force Direction. / Gomez, Augusto; Rano, Ignacio; Coleman, SA; McGinnity, T.Martin.

Unknown Host Publication. 2017.

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

TY - GEN

T1 - Towards Robot-Human Reliable Hand-over: Continuous Detection of Object Perturbation Force Direction

AU - Gomez, Augusto

AU - Rano, Ignacio

AU - Coleman, SA

AU - McGinnity, T.Martin

PY - 2017/5/30

Y1 - 2017/5/30

N2 - A fundamental aspect of many human-robot col- laborative tasks is object exchange or handover. Several tech- niques have been proposed to decide when a robot hand or gripper should release an object for a human to receive. However, these techniques typically neglect the reliability of the handover, assuming the process will occur without issue. Based on the fact that humans apply pulling forces in specific directions when receiving an object, this paper presents a recursive procedure enabling a robot to release an object appropriately and timely during a handover. Experiments with naive users showed subject-specific consistent pulling directions during robot-human handovers, highlighting the need for a system to be capable of detecting force directions in relation to objects. The approach reported in this paper shows that through tactile sensing the proposed approach can accurately classify between five different actions impacting an object held by a robot hand. The recursive nature of the system also enables detection of sequences of different actions, enabling the robot to decide to safely release the object only when the pulling performed by the human is in the right direction.

AB - A fundamental aspect of many human-robot col- laborative tasks is object exchange or handover. Several tech- niques have been proposed to decide when a robot hand or gripper should release an object for a human to receive. However, these techniques typically neglect the reliability of the handover, assuming the process will occur without issue. Based on the fact that humans apply pulling forces in specific directions when receiving an object, this paper presents a recursive procedure enabling a robot to release an object appropriately and timely during a handover. Experiments with naive users showed subject-specific consistent pulling directions during robot-human handovers, highlighting the need for a system to be capable of detecting force directions in relation to objects. The approach reported in this paper shows that through tactile sensing the proposed approach can accurately classify between five different actions impacting an object held by a robot hand. The recursive nature of the system also enables detection of sequences of different actions, enabling the robot to decide to safely release the object only when the pulling performed by the human is in the right direction.

KW - hand-overs

KW - grasping

KW - robotics

M3 - Conference contribution

BT - Unknown Host Publication

ER -