TY - GEN
T1 - May I talk about other shops here? Modeling territory and invasion in front of shops
AU - Satake, Satoru
AU - Iba, Hajime
AU - Kanda, Takayuki
AU - Imai, Michita
AU - Saiki, Yoichi Morales
N1 - Copyright:
Copyright 2014 Elsevier B.V., All rights reserved.
PY - 2014
Y1 - 2014
N2 - This paper models the concept of the "territory" of shops. First, we interviewed three shopkeepers and found that they perceived the space near their shop as their territory and that they interpreted some types of behaviors as invasive. Second, we confirmed that potential visitors share this notion of territory. We also confirmed that the size of the territory depends on the characteristics of a shop's facade. While there is little territory in front of walls, there is more territory in front of shelves and entrances. Our robot traversed around two real shopping malls that included 50 shops and took 3-D scans of their environment shapes. Each shop's facade was analyzed and the shop territory was computed. The computation results match people's perception. The recognition rate accuracy reached 93.5% for the territory areas. User evaluations in a virtual shop environment confirmed that a robot with a territory model behaves better than one without it.
AB - This paper models the concept of the "territory" of shops. First, we interviewed three shopkeepers and found that they perceived the space near their shop as their territory and that they interpreted some types of behaviors as invasive. Second, we confirmed that potential visitors share this notion of territory. We also confirmed that the size of the territory depends on the characteristics of a shop's facade. While there is little territory in front of walls, there is more territory in front of shelves and entrances. Our robot traversed around two real shopping malls that included 50 shops and took 3-D scans of their environment shapes. Each shop's facade was analyzed and the shop territory was computed. The computation results match people's perception. The recognition rate accuracy reached 93.5% for the territory areas. User evaluations in a virtual shop environment confirmed that a robot with a territory model behaves better than one without it.
KW - Concept of territory
KW - Human-robot interaction
KW - Social robots
UR - http://www.scopus.com/inward/record.url?scp=84897012670&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84897012670&partnerID=8YFLogxK
U2 - 10.1145/2559636.2559669
DO - 10.1145/2559636.2559669
M3 - Conference contribution
AN - SCOPUS:84897012670
SN - 9781450326582
T3 - ACM/IEEE International Conference on Human-Robot Interaction
SP - 487
EP - 494
BT - HRI 2014 - Proceedings of the 2014 ACM/IEEE International Conference on Human-Robot Interaction
PB - IEEE Computer Society
T2 - 9th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2014
Y2 - 3 March 2014 through 6 March 2014
ER -