A study of reaching motions for collaborative human-robot interaction

Sara Sheikholeslami; Gilwoo Lee; Justin W. Hart; Siddhartha Srinivasa; Elizabeth A. Croft

doi:10.1007/978-3-030-33950-0_50

A study of reaching motions for collaborative human-robot interaction

Sara Sheikholeslami, Gilwoo Lee, Justin W. Hart, Siddhartha Srinivasa, Elizabeth A. Croft

Electrical and Computer Systems Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

Abstract

In human-human interactions, individuals naturally achieve fluency by anticipating the partner’s actions. This predictive ability is largely lacking in collaborative robots, leading to inefficient human-robot interactions. Fluent meshing in human-robot collaboration requires the robot to make its intentions clear to its human collaborator. We propose a unified generative model of human reaching motions that allows the robot to (a) infer human intent, and then (b) plan its motion to be legible, or intent-expressive. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.

Original language	English
Title of host publication	Proceedings of the 2018 International Symposium on Experimental Robotics
Editors	Jing Xiao, Torsten Kröger, Oussama Khatib
Place of Publication	Cham Switzerland
Publisher	Springer
Pages	584-594
Number of pages	11
ISBN (Electronic)	9783030339500
ISBN (Print)	9783030339494
DOIs	https://doi.org/10.1007/978-3-030-33950-0_50
Publication status	Published - 2020
Event	International Symposium on Experimental Robotics 2018 - Buenos Aires, Argentina Duration: 5 Nov 2018 → 8 Nov 2018 https://link.springer.com/book/10.1007/978-3-030-33950-0

Publication series

Name	Springer Proceedings in Advanced Robotics
Publisher	Springer
Volume	11
ISSN (Print)	2511-1256
ISSN (Electronic)	2511-1264

Conference

Conference	International Symposium on Experimental Robotics 2018
Abbreviated title	ISER 2018
Country/Territory	Argentina
City	Buenos Aires
Period	5/11/18 → 8/11/18
Internet address	https://link.springer.com/book/10.1007/978-3-030-33950-0

Access to Document

10.1007/978-3-030-33950-0_50

Cite this

Sheikholeslami, S., Lee, G., Hart, J. W., Srinivasa, S., & Croft, E. A. (2020). A study of reaching motions for collaborative human-robot interaction. In J. Xiao, T. Kröger, & O. Khatib (Eds.), Proceedings of the 2018 International Symposium on Experimental Robotics (pp. 584-594). (Springer Proceedings in Advanced Robotics; Vol. 11). Springer. https://doi.org/10.1007/978-3-030-33950-0_50

@inproceedings{8ecd5dd5dce044ac82aad3cabdd89002,

title = "A study of reaching motions for collaborative human-robot interaction",

abstract = "In human-human interactions, individuals naturally achieve fluency by anticipating the partner{\textquoteright}s actions. This predictive ability is largely lacking in collaborative robots, leading to inefficient human-robot interactions. Fluent meshing in human-robot collaboration requires the robot to make its intentions clear to its human collaborator. We propose a unified generative model of human reaching motions that allows the robot to (a) infer human intent, and then (b) plan its motion to be legible, or intent-expressive. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.",

author = "Sara Sheikholeslami and Gilwoo Lee and Hart, {Justin W.} and Siddhartha Srinivasa and Croft, {Elizabeth A.}",

note = "Publisher Copyright: {\textcopyright} 2020, Springer Nature Switzerland AG.; International Symposium on Experimental Robotics 2018, ISER 2018 ; Conference date: 05-11-2018 Through 08-11-2018",

year = "2020",

doi = "10.1007/978-3-030-33950-0_50",

language = "English",

isbn = "9783030339494",

series = "Springer Proceedings in Advanced Robotics",

publisher = "Springer",

pages = "584--594",

editor = "Jing Xiao and Torsten Kr{\"o}ger and Oussama Khatib",

booktitle = "Proceedings of the 2018 International Symposium on Experimental Robotics",

url = "https://link.springer.com/book/10.1007/978-3-030-33950-0",

}

Sheikholeslami, S, Lee, G, Hart, JW, Srinivasa, S & Croft, EA 2020, A study of reaching motions for collaborative human-robot interaction. in J Xiao, T Kröger & O Khatib (eds), Proceedings of the 2018 International Symposium on Experimental Robotics. Springer Proceedings in Advanced Robotics, vol. 11, Springer, Cham Switzerland, pp. 584-594, International Symposium on Experimental Robotics 2018, Buenos Aires, Argentina, 5/11/18. https://doi.org/10.1007/978-3-030-33950-0_50

A study of reaching motions for collaborative human-robot interaction. / Sheikholeslami, Sara; Lee, Gilwoo; Hart, Justin W. et al.
Proceedings of the 2018 International Symposium on Experimental Robotics. ed. / Jing Xiao; Torsten Kröger; Oussama Khatib. Cham Switzerland: Springer, 2020. p. 584-594 (Springer Proceedings in Advanced Robotics; Vol. 11).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research

TY - GEN

T1 - A study of reaching motions for collaborative human-robot interaction

AU - Sheikholeslami, Sara

AU - Lee, Gilwoo

AU - Hart, Justin W.

AU - Srinivasa, Siddhartha

AU - Croft, Elizabeth A.

PY - 2020

Y1 - 2020

N2 - In human-human interactions, individuals naturally achieve fluency by anticipating the partner’s actions. This predictive ability is largely lacking in collaborative robots, leading to inefficient human-robot interactions. Fluent meshing in human-robot collaboration requires the robot to make its intentions clear to its human collaborator. We propose a unified generative model of human reaching motions that allows the robot to (a) infer human intent, and then (b) plan its motion to be legible, or intent-expressive. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.

AB - In human-human interactions, individuals naturally achieve fluency by anticipating the partner’s actions. This predictive ability is largely lacking in collaborative robots, leading to inefficient human-robot interactions. Fluent meshing in human-robot collaboration requires the robot to make its intentions clear to its human collaborator. We propose a unified generative model of human reaching motions that allows the robot to (a) infer human intent, and then (b) plan its motion to be legible, or intent-expressive. We conducted a study on human reaching motion and constructed an elliptical motion model that is shown to yield a good fit to empirical data. In future studies, we plan to confirm the effectiveness of this model in predicting human intent and conveying robot intent for achieving fluency in human-robot handovers.

UR - http://www.scopus.com/inward/record.url?scp=85107057338&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-33950-0_50

DO - 10.1007/978-3-030-33950-0_50

M3 - Conference Paper

AN - SCOPUS:85107057338

SN - 9783030339494

T3 - Springer Proceedings in Advanced Robotics

SP - 584

EP - 594

BT - Proceedings of the 2018 International Symposium on Experimental Robotics

A2 - Xiao, Jing

A2 - Kröger, Torsten

A2 - Khatib, Oussama

PB - Springer

CY - Cham Switzerland

T2 - International Symposium on Experimental Robotics 2018

Y2 - 5 November 2018 through 8 November 2018

ER -

A study of reaching motions for collaborative human-robot interaction

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this