From multicultural agents to culture‐aware robots

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

6 Citationer (Scopus)
465 Downloads (Pure)

Resumé

In previous research we showed how a cross‐cultural multimodal corpus of human face to face interactions can serve as empirical foundation for implementing multicultural agents (e.g. Rehm et al. 2009). To this end, the corpus has been annotated in relation to a number of communicative phenomena like gestures, postures, proxemics, communication management, etc. Based on these annotations, statistical models have been derived and implemented in embodied conversational agents in order to simulate culturespecific communicative behavior in these agents.
Although this was a successful approach, there have always been some discomforts about it due to the following reasons:
- Subjectivity of the annotation
- Cultural bias of the annotation and the implementation/design of the agents
- Applicability of results to agents (they might represent a culture of their own)

Meanwhile, we have moved to physical agents, i.e. robots. Here the difference between humans and robots is more apparent, due e.g. to limited expressive channels or reduced degrees of freedom. For instance the Nao platform which we are using has less joints in arms and legs then a human, making movements look different, independent on how careful movements have been designed.

Thus, we suggest a new methodological approach for modeling the behavior of robots and for making them culturally aware which could also be of benefit for the use in multicultural agents. Instead of collecting data from human interactions, potential users of the system have to create the behavior themselves, allowing us to collect a cross‐cultural database of behavioral parameters for the robotic system under development. This reduces any subjective or cultural bias that was previously introduced. Instead, the cross‐cultural database of behavioral parameters allows data‐mining the statistical models that will drive the generation of communicative behavior in the robot based on informants that are immersed in the target culture.
OriginalsprogEngelsk
TitelHuman-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments : 15th International Conference, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part III
RedaktørerMasaaki Kurosu
Antal sider10
ForlagSpringer Publishing Company
Publikationsdato2013
Sider431-440
ISBN (Trykt)978-3-642-39231-3
ISBN (Elektronisk)978-3-642-39232-0
DOI
StatusUdgivet - 2013
Begivenhed15th International Conference on Human-Computer Interaction (HCI International 2013) - Las Vegas, USA
Varighed: 21 jul. 201326 jul. 2013

Konference

Konference15th International Conference on Human-Computer Interaction (HCI International 2013)
LandUSA
ByLas Vegas
Periode21/07/201326/07/2013
NavnLecture Notes in Computer Science (LNCS)
ISSN0302-9743

Fingerprint

Robots
Robotics
Communication
Statistical Models

Citer dette

Rehm, M. (2013). From multicultural agents to culture‐aware robots. I M. Kurosu (red.), Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments: 15th International Conference, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part III (s. 431-440). Springer Publishing Company. Lecture Notes in Computer Science (LNCS) https://doi.org/10.1007/978-3-642-39232-0_47
Rehm, Matthias. / From multicultural agents to culture‐aware robots. Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments: 15th International Conference, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part III. red. / Masaaki Kurosu. Springer Publishing Company, 2013. s. 431-440 (Lecture Notes in Computer Science (LNCS)).
@inproceedings{947c437e793e46dbab38c63db0128a06,
title = "From multicultural agents to culture‐aware robots",
abstract = "In previous research we showed how a cross‐cultural multimodal corpus of human face to face interactions can serve as empirical foundation for implementing multicultural agents (e.g. Rehm et al. 2009). To this end, the corpus has been annotated in relation to a number of communicative phenomena like gestures, postures, proxemics, communication management, etc. Based on these annotations, statistical models have been derived and implemented in embodied conversational agents in order to simulate culturespecific communicative behavior in these agents.Although this was a successful approach, there have always been some discomforts about it due to the following reasons:- Subjectivity of the annotation- Cultural bias of the annotation and the implementation/design of the agents- Applicability of results to agents (they might represent a culture of their own)Meanwhile, we have moved to physical agents, i.e. robots. Here the difference between humans and robots is more apparent, due e.g. to limited expressive channels or reduced degrees of freedom. For instance the Nao platform which we are using has less joints in arms and legs then a human, making movements look different, independent on how careful movements have been designed.Thus, we suggest a new methodological approach for modeling the behavior of robots and for making them culturally aware which could also be of benefit for the use in multicultural agents. Instead of collecting data from human interactions, potential users of the system have to create the behavior themselves, allowing us to collect a cross‐cultural database of behavioral parameters for the robotic system under development. This reduces any subjective or cultural bias that was previously introduced. Instead, the cross‐cultural database of behavioral parameters allows data‐mining the statistical models that will drive the generation of communicative behavior in the robot based on informants that are immersed in the target culture.",
keywords = "Culture Aware Robots, Human robot interaction, Affective Computing",
author = "Matthias Rehm",
year = "2013",
doi = "10.1007/978-3-642-39232-0_47",
language = "English",
isbn = "978-3-642-39231-3",
series = "Lecture Notes in Computer Science (LNCS)",
publisher = "Springer Publishing Company",
pages = "431--440",
editor = "Masaaki Kurosu",
booktitle = "Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments",
address = "United States",

}

Rehm, M 2013, From multicultural agents to culture‐aware robots. i M Kurosu (red.), Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments: 15th International Conference, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part III. Springer Publishing Company, Lecture Notes in Computer Science (LNCS), s. 431-440, 15th International Conference on Human-Computer Interaction (HCI International 2013), Las Vegas, USA, 21/07/2013. https://doi.org/10.1007/978-3-642-39232-0_47

From multicultural agents to culture‐aware robots. / Rehm, Matthias.

Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments: 15th International Conference, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part III. red. / Masaaki Kurosu. Springer Publishing Company, 2013. s. 431-440 (Lecture Notes in Computer Science (LNCS)).

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - From multicultural agents to culture‐aware robots

AU - Rehm, Matthias

PY - 2013

Y1 - 2013

N2 - In previous research we showed how a cross‐cultural multimodal corpus of human face to face interactions can serve as empirical foundation for implementing multicultural agents (e.g. Rehm et al. 2009). To this end, the corpus has been annotated in relation to a number of communicative phenomena like gestures, postures, proxemics, communication management, etc. Based on these annotations, statistical models have been derived and implemented in embodied conversational agents in order to simulate culturespecific communicative behavior in these agents.Although this was a successful approach, there have always been some discomforts about it due to the following reasons:- Subjectivity of the annotation- Cultural bias of the annotation and the implementation/design of the agents- Applicability of results to agents (they might represent a culture of their own)Meanwhile, we have moved to physical agents, i.e. robots. Here the difference between humans and robots is more apparent, due e.g. to limited expressive channels or reduced degrees of freedom. For instance the Nao platform which we are using has less joints in arms and legs then a human, making movements look different, independent on how careful movements have been designed.Thus, we suggest a new methodological approach for modeling the behavior of robots and for making them culturally aware which could also be of benefit for the use in multicultural agents. Instead of collecting data from human interactions, potential users of the system have to create the behavior themselves, allowing us to collect a cross‐cultural database of behavioral parameters for the robotic system under development. This reduces any subjective or cultural bias that was previously introduced. Instead, the cross‐cultural database of behavioral parameters allows data‐mining the statistical models that will drive the generation of communicative behavior in the robot based on informants that are immersed in the target culture.

AB - In previous research we showed how a cross‐cultural multimodal corpus of human face to face interactions can serve as empirical foundation for implementing multicultural agents (e.g. Rehm et al. 2009). To this end, the corpus has been annotated in relation to a number of communicative phenomena like gestures, postures, proxemics, communication management, etc. Based on these annotations, statistical models have been derived and implemented in embodied conversational agents in order to simulate culturespecific communicative behavior in these agents.Although this was a successful approach, there have always been some discomforts about it due to the following reasons:- Subjectivity of the annotation- Cultural bias of the annotation and the implementation/design of the agents- Applicability of results to agents (they might represent a culture of their own)Meanwhile, we have moved to physical agents, i.e. robots. Here the difference between humans and robots is more apparent, due e.g. to limited expressive channels or reduced degrees of freedom. For instance the Nao platform which we are using has less joints in arms and legs then a human, making movements look different, independent on how careful movements have been designed.Thus, we suggest a new methodological approach for modeling the behavior of robots and for making them culturally aware which could also be of benefit for the use in multicultural agents. Instead of collecting data from human interactions, potential users of the system have to create the behavior themselves, allowing us to collect a cross‐cultural database of behavioral parameters for the robotic system under development. This reduces any subjective or cultural bias that was previously introduced. Instead, the cross‐cultural database of behavioral parameters allows data‐mining the statistical models that will drive the generation of communicative behavior in the robot based on informants that are immersed in the target culture.

KW - Culture Aware Robots

KW - Human robot interaction

KW - Affective Computing

UR - http://www.scopus.com/inward/record.url?scp=84880679237&partnerID=8YFLogxK

U2 - 10.1007/978-3-642-39232-0_47

DO - 10.1007/978-3-642-39232-0_47

M3 - Article in proceeding

SN - 978-3-642-39231-3

T3 - Lecture Notes in Computer Science (LNCS)

SP - 431

EP - 440

BT - Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments

A2 - Kurosu, Masaaki

PB - Springer Publishing Company

ER -

Rehm M. From multicultural agents to culture‐aware robots. I Kurosu M, red., Human-Computer Interaction. Human-Centred Design Approaches, Methods, Tools, and Environments: 15th International Conference, HCI International 2013, Las Vegas, NV, USA, July 21-26, 2013, Proceedings, Part III. Springer Publishing Company. 2013. s. 431-440. (Lecture Notes in Computer Science (LNCS)). https://doi.org/10.1007/978-3-642-39232-0_47