Abstract
way for non-experts to teach new skills to a robot. PbD can
be carried out in different ways, for instance, by kinesthetic guidance,
teleoperation or by using external controls. In this paper,
we compare these three ways of controlling a robot in terms of
efficiency, effectiveness (success and error rate) and usability. In
an industrial assembly scenario, 51 participants carried out pegin-
hole tasks using one of the three control modalities. The results
show that kinesthetic guidance produces the best results. In order
to test whether the problems during teleoperation are due to
the fact that users cannot, like in kinesthetic guidance, switch
between control points using traditional teleoperation devices, we
designed a new device that allows users to switch between controls
for large and small movements. A user study with 15 participants
shows that the novel teleoperation device yields almost as good
results as kinesthetic guidance.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of the 11th ACM/IEEE International Conference on Human-Robot Interaction |
| Editors | Christoph Bartneck, Yukie Nagai, Ana Paiva, Selma Šabanović |
| Place of Publication | New Jersey, USA |
| Publisher | IEEE Press |
| Publication date | 2016 |
| Pages | 213-220 |
| ISBN (Print) | 978-1-4673-8369-1 |
| ISBN (Electronic) | 978-1-4673-8370-7 |
| DOIs | |
| Publication status | Published - 2016 |
| Event | 11th ACM/IEEE International Conference on Human Robot Interaction - Christchurch, New Zealand Duration: 7. Mar 2016 → 10. Mar 2016 |
Conference
| Conference | 11th ACM/IEEE International Conference on Human Robot Interaction |
|---|---|
| Country | New Zealand |
| City | Christchurch |
| Period | 07/03/2016 → 10/03/2016 |
Fingerprint
Keywords
- teleoperation
- kinesthetic guidance
- learning from demonstration
- interface design
Cite this
}
A Comparison of Types of Robot Control for Programming by Demonstration. / Fischer, Kerstin; Kirstein, Franziska; Jensen, Lars Christian; Krüger, Norbert; Kuklinski, Kamil; aus der Wieschen, Maria Vanessa; Savarimuthu, Thiusius Rajeeth.
Proceedings of the 11th ACM/IEEE International Conference on Human-Robot Interaction. ed. / Christoph Bartneck; Yukie Nagai; Ana Paiva; Selma Šabanović. New Jersey, USA : IEEE Press, 2016. p. 213-220.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
TY - GEN
T1 - A Comparison of Types of Robot Control for Programming by Demonstration
AU - Fischer, Kerstin
AU - Kirstein, Franziska
AU - Jensen, Lars Christian
AU - Krüger, Norbert
AU - Kuklinski, Kamil
AU - aus der Wieschen, Maria Vanessa
AU - Savarimuthu, Thiusius Rajeeth
PY - 2016
Y1 - 2016
N2 - Programming by Demonstration (PbD) is an efficientway for non-experts to teach new skills to a robot. PbD canbe carried out in different ways, for instance, by kinesthetic guidance,teleoperation or by using external controls. In this paper,we compare these three ways of controlling a robot in terms ofefficiency, effectiveness (success and error rate) and usability. Inan industrial assembly scenario, 51 participants carried out pegin-hole tasks using one of the three control modalities. The resultsshow that kinesthetic guidance produces the best results. In orderto test whether the problems during teleoperation are due tothe fact that users cannot, like in kinesthetic guidance, switchbetween control points using traditional teleoperation devices, wedesigned a new device that allows users to switch between controlsfor large and small movements. A user study with 15 participantsshows that the novel teleoperation device yields almost as goodresults as kinesthetic guidance.
AB - Programming by Demonstration (PbD) is an efficientway for non-experts to teach new skills to a robot. PbD canbe carried out in different ways, for instance, by kinesthetic guidance,teleoperation or by using external controls. In this paper,we compare these three ways of controlling a robot in terms ofefficiency, effectiveness (success and error rate) and usability. Inan industrial assembly scenario, 51 participants carried out pegin-hole tasks using one of the three control modalities. The resultsshow that kinesthetic guidance produces the best results. In orderto test whether the problems during teleoperation are due tothe fact that users cannot, like in kinesthetic guidance, switchbetween control points using traditional teleoperation devices, wedesigned a new device that allows users to switch between controlsfor large and small movements. A user study with 15 participantsshows that the novel teleoperation device yields almost as goodresults as kinesthetic guidance.
KW - teleoperation
KW - kinesthetic guidance
KW - learning from demonstration
KW - interface design
U2 - 10.1109/HRI.2016.7451754
DO - 10.1109/HRI.2016.7451754
M3 - Article in proceedings
SN - 978-1-4673-8369-1
SP - 213
EP - 220
BT - Proceedings of the 11th ACM/IEEE International Conference on Human-Robot Interaction
A2 - Bartneck, Christoph
A2 - Nagai, Yukie
A2 - Paiva, Ana
A2 - Šabanović, Selma
PB - IEEE Press
CY - New Jersey, USA
ER -