Projecting robot intentions into human environments

Rasmus S. Andersen, Ole Madsen, Thomas B. Moeslund, Hani Ben Amor

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

18 Citations (Scopus)

Abstract

Trained human co-workers can often easily predict each other's intentions based on prior experience. When collaborating with a robot coworker, however, intentions are hard or impossible to infer. This difficulty of mental introspection makes human-robot collaboration challenging and can lead to dangerous misunderstandings. In this paper, we present a novel, object-aware projection technique that allows robots to visualize task information and intentions on physical objects in the environment. The approach uses modern object tracking methods in order to display information at specific spatial locations taking into account the pose and shape of surrounding objects. As a result, a human co-worker can be informed in a timely manner about the safety of the workspace, the site of next robot manipulation tasks, and next subtasks to perform. A preliminary usability study compares the approach to collaboration approaches based on monitors and printed text. The study indicates that, on average, the user effectiveness and satisfaction is higher with the projection based approach.

Original languageEnglish (US)
Title of host publication25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages294-301
Number of pages8
ISBN (Electronic)9781509039296
DOIs
StatePublished - Nov 15 2016
Event25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016 - New York, United States
Duration: Aug 26 2016Aug 31 2016

Other

Other25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016
CountryUnited States
CityNew York
Period8/26/168/31/16

Fingerprint

Robots
Data Display
Safety

ASJC Scopus subject areas

  • Artificial Intelligence
  • Social Psychology
  • Human-Computer Interaction

Cite this

Andersen, R. S., Madsen, O., Moeslund, T. B., & Ben Amor, H. (2016). Projecting robot intentions into human environments. In 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016 (pp. 294-301). [7745145] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROMAN.2016.7745145

Projecting robot intentions into human environments. / Andersen, Rasmus S.; Madsen, Ole; Moeslund, Thomas B.; Ben Amor, Hani.

25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 294-301 7745145.

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

Andersen, RS, Madsen, O, Moeslund, TB & Ben Amor, H 2016, Projecting robot intentions into human environments. in 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016., 7745145, Institute of Electrical and Electronics Engineers Inc., pp. 294-301, 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016, New York, United States, 8/26/16. https://doi.org/10.1109/ROMAN.2016.7745145
Andersen RS, Madsen O, Moeslund TB, Ben Amor H. Projecting robot intentions into human environments. In 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 294-301. 7745145 https://doi.org/10.1109/ROMAN.2016.7745145
Andersen, Rasmus S. ; Madsen, Ole ; Moeslund, Thomas B. ; Ben Amor, Hani. / Projecting robot intentions into human environments. 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 294-301
@inproceedings{2790dcd300f64d95b60d6a3d3f4d6686,
title = "Projecting robot intentions into human environments",
abstract = "Trained human co-workers can often easily predict each other's intentions based on prior experience. When collaborating with a robot coworker, however, intentions are hard or impossible to infer. This difficulty of mental introspection makes human-robot collaboration challenging and can lead to dangerous misunderstandings. In this paper, we present a novel, object-aware projection technique that allows robots to visualize task information and intentions on physical objects in the environment. The approach uses modern object tracking methods in order to display information at specific spatial locations taking into account the pose and shape of surrounding objects. As a result, a human co-worker can be informed in a timely manner about the safety of the workspace, the site of next robot manipulation tasks, and next subtasks to perform. A preliminary usability study compares the approach to collaboration approaches based on monitors and printed text. The study indicates that, on average, the user effectiveness and satisfaction is higher with the projection based approach.",
author = "Andersen, {Rasmus S.} and Ole Madsen and Moeslund, {Thomas B.} and {Ben Amor}, Hani",
year = "2016",
month = "11",
day = "15",
doi = "10.1109/ROMAN.2016.7745145",
language = "English (US)",
pages = "294--301",
booktitle = "25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Projecting robot intentions into human environments

AU - Andersen, Rasmus S.

AU - Madsen, Ole

AU - Moeslund, Thomas B.

AU - Ben Amor, Hani

PY - 2016/11/15

Y1 - 2016/11/15

N2 - Trained human co-workers can often easily predict each other's intentions based on prior experience. When collaborating with a robot coworker, however, intentions are hard or impossible to infer. This difficulty of mental introspection makes human-robot collaboration challenging and can lead to dangerous misunderstandings. In this paper, we present a novel, object-aware projection technique that allows robots to visualize task information and intentions on physical objects in the environment. The approach uses modern object tracking methods in order to display information at specific spatial locations taking into account the pose and shape of surrounding objects. As a result, a human co-worker can be informed in a timely manner about the safety of the workspace, the site of next robot manipulation tasks, and next subtasks to perform. A preliminary usability study compares the approach to collaboration approaches based on monitors and printed text. The study indicates that, on average, the user effectiveness and satisfaction is higher with the projection based approach.

AB - Trained human co-workers can often easily predict each other's intentions based on prior experience. When collaborating with a robot coworker, however, intentions are hard or impossible to infer. This difficulty of mental introspection makes human-robot collaboration challenging and can lead to dangerous misunderstandings. In this paper, we present a novel, object-aware projection technique that allows robots to visualize task information and intentions on physical objects in the environment. The approach uses modern object tracking methods in order to display information at specific spatial locations taking into account the pose and shape of surrounding objects. As a result, a human co-worker can be informed in a timely manner about the safety of the workspace, the site of next robot manipulation tasks, and next subtasks to perform. A preliminary usability study compares the approach to collaboration approaches based on monitors and printed text. The study indicates that, on average, the user effectiveness and satisfaction is higher with the projection based approach.

UR - http://www.scopus.com/inward/record.url?scp=85002780138&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85002780138&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2016.7745145

DO - 10.1109/ROMAN.2016.7745145

M3 - Conference contribution

SP - 294

EP - 301

BT - 25th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -