Human Manipulation Segmentation and Characterization Based on Instantaneous Work

Anthony Remazeilles; Irati Rasines; Asier Fernandez; Joseph McIntyre

doi:10.1007/978-3-030-35990-4_28

Human Manipulation Segmentation and Characterization Based on Instantaneous Work

Anthony Remazeilles, Irati Rasines, Asier Fernandez, Joseph McIntyre

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This paper is related to the observation of human operator manipulating objects for teaching a robot to reproduce the action. Assuming the robotic system is equipped with basic manipulation skills, we focus here on the automatic segmentation of the observed manipulation, for extracting the relevant key frames in which the manipulation is best described. The segmentation method proposed is based on the instantaneous work, and presents the advantage of not depending on the force and pose sensing locations. The proposed approach is experimented with two different manipulation skills, sliding and folding, under different settings.

Original language	English
Title of host publication	Robot 2019
Subtitle of host publication	4th Iberian Robotics Conference - Advances in Robotics
Editors	Manuel F. Silva, José Luís Lima, Luís Paulo Reis, Alberto Sanfeliu, Danilo Tardioli
Publisher	Springer
Pages	343-354
Number of pages	12
ISBN (Print)	9783030359898
DOIs	https://doi.org/10.1007/978-3-030-35990-4_28
Publication status	Published - 2020
Event	4th Iberian Robotics Conference, ROBOT 2019 - Porto, Portugal Duration: 20 Nov 2019 → 22 Nov 2019

Publication series

Name	Advances in Intelligent Systems and Computing
Volume	1092 AISC
ISSN (Print)	2194-5357
ISSN (Electronic)	2194-5365

Conference

Conference	4th Iberian Robotics Conference, ROBOT 2019
Country/Territory	Portugal
City	Porto
Period	20/11/19 → 22/11/19

Keywords

Manipulation segmentation
Teaching by demonstration

Access to Document

10.1007/978-3-030-35990-4_28

Cite this

Remazeilles, A., Rasines, I., Fernandez, A., & McIntyre, J. (2020). Human Manipulation Segmentation and Characterization Based on Instantaneous Work. In M. F. Silva, J. Luís Lima, L. P. Reis, A. Sanfeliu, & D. Tardioli (Eds.), Robot 2019: 4th Iberian Robotics Conference - Advances in Robotics (pp. 343-354). (Advances in Intelligent Systems and Computing; Vol. 1092 AISC). Springer. https://doi.org/10.1007/978-3-030-35990-4_28

Remazeilles, Anthony ; Rasines, Irati ; Fernandez, Asier et al. / Human Manipulation Segmentation and Characterization Based on Instantaneous Work. Robot 2019: 4th Iberian Robotics Conference - Advances in Robotics. editor / Manuel F. Silva ; José Luís Lima ; Luís Paulo Reis ; Alberto Sanfeliu ; Danilo Tardioli. Springer, 2020. pp. 343-354 (Advances in Intelligent Systems and Computing).

@inproceedings{b4d7fe28b7a844778e1da21e5b087c3a,

title = "Human Manipulation Segmentation and Characterization Based on Instantaneous Work",

abstract = "This paper is related to the observation of human operator manipulating objects for teaching a robot to reproduce the action. Assuming the robotic system is equipped with basic manipulation skills, we focus here on the automatic segmentation of the observed manipulation, for extracting the relevant key frames in which the manipulation is best described. The segmentation method proposed is based on the instantaneous work, and presents the advantage of not depending on the force and pose sensing locations. The proposed approach is experimented with two different manipulation skills, sliding and folding, under different settings.",

keywords = "Manipulation segmentation, Teaching by demonstration",

author = "Anthony Remazeilles and Irati Rasines and Asier Fernandez and Joseph McIntyre",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; 4th Iberian Robotics Conference, ROBOT 2019 ; Conference date: 20-11-2019 Through 22-11-2019",

year = "2020",

doi = "10.1007/978-3-030-35990-4_28",

language = "English",

isbn = "9783030359898",

series = "Advances in Intelligent Systems and Computing",

publisher = "Springer",

pages = "343--354",

editor = "Silva, {Manuel F.} and {Lu{\'i}s Lima}, Jos{\'e} and Reis, {Lu{\'i}s Paulo} and Alberto Sanfeliu and Danilo Tardioli",

booktitle = "Robot 2019",

address = "Germany",

}

Remazeilles, A , Rasines, I , Fernandez, A & McIntyre, J 2020, Human Manipulation Segmentation and Characterization Based on Instantaneous Work. in MF Silva, J Luís Lima, LP Reis, A Sanfeliu & D Tardioli (eds), Robot 2019: 4th Iberian Robotics Conference - Advances in Robotics. Advances in Intelligent Systems and Computing, vol. 1092 AISC, Springer, pp. 343-354, 4th Iberian Robotics Conference, ROBOT 2019, Porto, Portugal, 20/11/19. https://doi.org/10.1007/978-3-030-35990-4_28

Human Manipulation Segmentation and Characterization Based on Instantaneous Work. / Remazeilles, Anthony ; Rasines, Irati ; Fernandez, Asier et al.
Robot 2019: 4th Iberian Robotics Conference - Advances in Robotics. ed. / Manuel F. Silva; José Luís Lima; Luís Paulo Reis; Alberto Sanfeliu; Danilo Tardioli. Springer, 2020. p. 343-354 (Advances in Intelligent Systems and Computing; Vol. 1092 AISC).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Human Manipulation Segmentation and Characterization Based on Instantaneous Work

AU - Remazeilles, Anthony

AU - Rasines, Irati

AU - Fernandez, Asier

AU - McIntyre, Joseph

PY - 2020

Y1 - 2020

N2 - This paper is related to the observation of human operator manipulating objects for teaching a robot to reproduce the action. Assuming the robotic system is equipped with basic manipulation skills, we focus here on the automatic segmentation of the observed manipulation, for extracting the relevant key frames in which the manipulation is best described. The segmentation method proposed is based on the instantaneous work, and presents the advantage of not depending on the force and pose sensing locations. The proposed approach is experimented with two different manipulation skills, sliding and folding, under different settings.

AB - This paper is related to the observation of human operator manipulating objects for teaching a robot to reproduce the action. Assuming the robotic system is equipped with basic manipulation skills, we focus here on the automatic segmentation of the observed manipulation, for extracting the relevant key frames in which the manipulation is best described. The segmentation method proposed is based on the instantaneous work, and presents the advantage of not depending on the force and pose sensing locations. The proposed approach is experimented with two different manipulation skills, sliding and folding, under different settings.

KW - Manipulation segmentation

KW - Teaching by demonstration

UR - http://www.scopus.com/inward/record.url?scp=85082137099&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-35990-4_28

DO - 10.1007/978-3-030-35990-4_28

M3 - Conference contribution

AN - SCOPUS:85082137099

SN - 9783030359898

T3 - Advances in Intelligent Systems and Computing

SP - 343

EP - 354

BT - Robot 2019

A2 - Silva, Manuel F.

A2 - Luís Lima, José

A2 - Reis, Luís Paulo

A2 - Sanfeliu, Alberto

A2 - Tardioli, Danilo

PB - Springer

T2 - 4th Iberian Robotics Conference, ROBOT 2019

Y2 - 20 November 2019 through 22 November 2019

ER -

Remazeilles A , Rasines I , Fernandez A , McIntyre J. Human Manipulation Segmentation and Characterization Based on Instantaneous Work. In Silva MF, Luís Lima J, Reis LP, Sanfeliu A, Tardioli D, editors, Robot 2019: 4th Iberian Robotics Conference - Advances in Robotics. Springer. 2020. p. 343-354. (Advances in Intelligent Systems and Computing). doi: 10.1007/978-3-030-35990-4_28

Human Manipulation Segmentation and Characterization Based on Instantaneous Work

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this