Towards a computational theory of cognitive maps
Artificial Intelligence
Behavioral Experiments in Spatial Cognition Using Virtual Reality
Spatial Cognition, An Interdisciplinary Approach to Representing and Processing Spatial Knowledge
Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)
Probabilistic Robotics (Intelligent Robotics and Autonomous Agents)
Supervised semantic labeling of places using information extracted from sensor data
Robotics and Autonomous Systems
Proceedings of the 4th ACM/IEEE international conference on Human robot interaction
Robots asking for directions: the willingness of passers-by to support robots
Proceedings of the 5th ACM/IEEE international conference on Human-robot interaction
Do we need to walk for effective virtual reality navigation? physical rotations alone may suffice
SC'10 Proceedings of the 7th international conference on Spatial cognition
Do elderly people prefer a conversational humanoid as a shopping assistant partner in supermarkets?
Proceedings of the 6th international conference on Human-robot interaction
A Human Aware Mobile Robot Motion Planner
IEEE Transactions on Robotics
Understanding suitable locations for waiting
Proceedings of the 8th ACM/IEEE international conference on Human-robot interaction
Hi-index | 0.00 |
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.