Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction

Sara Sheikholeslami, Justin W. Hart, Wesley P. Chan, Camilo P. Quintero, Elizabeth A. Croft

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

Abstract

In human-human interactions, individuals naturally achieve fluency by anticipating the partners actions. This predictive ability is largely lacking in robots, leading to stilted human-robot interactions. We aim to improve fluency in human-robot reaching motions using a unified predictive model of human reaching motions. Using this model, we allow the robot to infer human intent, while also applying the same model to generate the robots motion to make its intent more transparent to the human. 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 languageEnglish
Title of host publicationCompanion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction
EditorsGuy Hoffman, Adriana Tapus
Place of PublicationNew York USA
PublisherAssociation for Computing Machinery (ACM)
Pages321-322
Number of pages2
DOIs
Publication statusPublished - 1 Mar 2018
Externally publishedYes
EventAnnual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2018 - Chicago, United States of America
Duration: 5 Mar 20188 Mar 2018
Conference number: 13th

Conference

ConferenceAnnual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2018
Abbreviated titleHRI 2018
CountryUnited States of America
CityChicago
Period5/03/188/03/18

Cite this

Sheikholeslami, S., Hart, J. W., Chan, W. P., Quintero, C. P., & Croft, E. A. (2018). Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction. In G. Hoffman, & A. Tapus (Eds.), Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction (pp. 321-322). New York USA: Association for Computing Machinery (ACM). https://doi.org/10.1145/3173386.3176924
Sheikholeslami, Sara ; Hart, Justin W. ; Chan, Wesley P. ; Quintero, Camilo P. ; Croft, Elizabeth A. / Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction. Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction. editor / Guy Hoffman ; Adriana Tapus. New York USA : Association for Computing Machinery (ACM), 2018. pp. 321-322
@inproceedings{319fdcb7acbe4ce6af09f2000e1440e5,
title = "Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction",
abstract = "In human-human interactions, individuals naturally achieve fluency by anticipating the partners actions. This predictive ability is largely lacking in robots, leading to stilted human-robot interactions. We aim to improve fluency in human-robot reaching motions using a unified predictive model of human reaching motions. Using this model, we allow the robot to infer human intent, while also applying the same model to generate the robots motion to make its intent more transparent to the human. 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 Hart, {Justin W.} and Chan, {Wesley P.} and Quintero, {Camilo P.} and Croft, {Elizabeth A.}",
year = "2018",
month = "3",
day = "1",
doi = "10.1145/3173386.3176924",
language = "English",
pages = "321--322",
editor = "Hoffman, {Guy } and Adriana Tapus",
booktitle = "Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction",
publisher = "Association for Computing Machinery (ACM)",
address = "United States of America",

}

Sheikholeslami, S, Hart, JW, Chan, WP, Quintero, CP & Croft, EA 2018, Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction. in G Hoffman & A Tapus (eds), Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction. Association for Computing Machinery (ACM), New York USA, pp. 321-322, Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI) 2018, Chicago, United States of America, 5/03/18. https://doi.org/10.1145/3173386.3176924

Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction. / Sheikholeslami, Sara; Hart, Justin W.; Chan, Wesley P.; Quintero, Camilo P.; Croft, Elizabeth A.

Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction. ed. / Guy Hoffman; Adriana Tapus. New York USA : Association for Computing Machinery (ACM), 2018. p. 321-322.

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

TY - GEN

T1 - Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction

AU - Sheikholeslami, Sara

AU - Hart, Justin W.

AU - Chan, Wesley P.

AU - Quintero, Camilo P.

AU - Croft, Elizabeth A.

PY - 2018/3/1

Y1 - 2018/3/1

N2 - In human-human interactions, individuals naturally achieve fluency by anticipating the partners actions. This predictive ability is largely lacking in robots, leading to stilted human-robot interactions. We aim to improve fluency in human-robot reaching motions using a unified predictive model of human reaching motions. Using this model, we allow the robot to infer human intent, while also applying the same model to generate the robots motion to make its intent more transparent to the human. 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 partners actions. This predictive ability is largely lacking in robots, leading to stilted human-robot interactions. We aim to improve fluency in human-robot reaching motions using a unified predictive model of human reaching motions. Using this model, we allow the robot to infer human intent, while also applying the same model to generate the robots motion to make its intent more transparent to the human. 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=85045237851&partnerID=8YFLogxK

U2 - 10.1145/3173386.3176924

DO - 10.1145/3173386.3176924

M3 - Conference Paper

SP - 321

EP - 322

BT - Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction

A2 - Hoffman, Guy

A2 - Tapus, Adriana

PB - Association for Computing Machinery (ACM)

CY - New York USA

ER -

Sheikholeslami S, Hart JW, Chan WP, Quintero CP, Croft EA. Prediction and Production of Human Reaching Trajectories for Human-Robot Interaction. In Hoffman G, Tapus A, editors, Companion of the 2018 ACM/IEEE International Conference on Human-Robot Interaction. New York USA: Association for Computing Machinery (ACM). 2018. p. 321-322 https://doi.org/10.1145/3173386.3176924