Analysis of human behavior to a communication robot in an open field

Nabe, S.; Kanda, Takayuki; Hiraki, Kei; Ishiguro, Hiroshi; Kiyokawa, Kiyoshi; Hagita, Norihiro

doi:10.1145/1121241.1121282

Cited by 17 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, when larger crowds formed around it, they seemed to get bolder; there was much more playing with the robot then, essentially turning it into an attraction of the arcade. This actually contradicts the results found in [22], where an experiment shows that if a person is close to the robot, other people tend not to get close to the robot also. -People in transit like e.g.…”

Section: Observationscontrasting

confidence: 84%

Pilot Study of Person Robot Interaction in a Public Transit Space

Svenstrup

Bak

Maler

et al. 2009

Communications in Computer and Information Science

View full text Add to dashboard Cite

This paper describes a study of the effect of a human interactive robot placed in an urban transit space. The underlying hypothesis is that it is possible to create interesting new living spaces and induce value in terms of experiences, information or economics, by putting socially interactive mobile agents into public urban transit area. To investigate the hypothesis, an experiment was carried out at a bus terminal serving both as a transit space and a shopping mall, where an autonomous robot were to detect and follow random people. The people that were followed were asked to fill out a questionnaire for quantitative analysis of the experiment. In addition video documentation of the experiment was used in the evaluation. The results showed that people were generally positive towards having mobile robots in this type of environment where shopping is combined with transit. However, it also showed harder than expected to start interaction with commuters due to their determination and speed towards their goal. Further it was demonstrated that it was possible to track and follow people, who were not beforehand informed on the experiment. The evaluation indicated, that the distance to initiate interaction was shorter than initially expected, but complies with the distance for normal human to human interaction.

show abstract

Section: Observationscontrasting

confidence: 84%

Pilot Study of Person Robot Interaction in a Public Transit Space

Svenstrup

Bak

Maler

et al. 2009

Communications in Computer and Information Science

View full text Add to dashboard Cite

show abstract

“…Our experimentation studied the influence of three animated objects whereas most of the others focused on one object (Nabe et al [18], Svenstrup et al [19], Weiss et al [20] and Beran et al [21]). …”

Section: Discussionmentioning

confidence: 99%

Ethological evaluation of human-robot Interaction: Are children more efficient and motivated with computer, virtual agent or robots?

Jost

André

Pévédic

et al. 2012

2012 IEEE International Conference on Robotics and Biomimetics (ROBIO)

View full text Add to dashboard Cite

Abstract-Nowadays, robots and virtual agents become companions for humans. They seem to have distinct roles in the Human-Agent Interaction. Thus, when developing a new application, it is judicious to wonder which the better is. In the Robadom project, a homecare robot has to assist elderly at home. The robot provides cognitive stimulation game. We developed StimCards, a cognitive card-based game. The principle question is: is the robot the best interlocutor in this context? This paper presents an evaluation of StimCards. Participants are children because French elderly is reluctant to robots and because they will be the future hypothetical users.

show abstract

“…It was assumed that people which entered that zone are interested in an interaction. Nabe et al [4] discovered in a field trial with a ROBOVIE-M robot that three zones exist in which a person shows either a watching, a talking or a physical interacting behavior depending on their distances to the robot. They announced to regulate the robot's behavior just by these distances.…”

Section: Related Workmentioning

confidence: 99%

Whom to talk to? Estimating user interest from movement trajectories

Müller

Hellbach

Schaffernicht

et al. 2008

RO-MAN 2008 - The 17th IEEE International Symposium on Robot and Human Interactive Communication

View full text Add to dashboard Cite

Correctly identifying people who are interested in an interaction with a mobile robot is an essential task for a smart Human-Robot Interaction.In this paper an approach is presented for selecting suitable trajectory features in a task specific manner from a huge amount of different forms of possible representations. Different sub-sampling techniques are proposed to generate trajectory sequences from which features are extracted. The trajectory data was generated in real world experiments that include extensive user interviews to acquire information about user behaviors and intentions. Using those feature vectors in a classification method enables the robot to estimate the user's interaction interest.For generating low-dimensional feature vectors, a common method, the Principle Component Analysis, is applied. The selection and combination of useful features out of a set of possible features is carried out by an information theoretic approach based on the Mutual Information and Joint Mutual Information with respect to the user's interaction interest. The introduced procedure is evaluated with neural classifiers, which are trained with the extracted features of the trajectories and the user behavior gained by observation as well as user interviewing. The results achieved indicate that an estimation of the user's interaction interest using trajectory information is feasible.

show abstract

Analysis of human behavior to a communication robot in an open field

Cited by 17 publications

References 17 publications

Pilot Study of Person Robot Interaction in a Public Transit Space

Pilot Study of Person Robot Interaction in a Public Transit Space

Ethological evaluation of human-robot Interaction: Are children more efficient and motivated with computer, virtual agent or robots?

Whom to talk to? Estimating user interest from movement trajectories

Contact Info

Product

Resources

About