2013 Fiscal Year Final Research Report
Modeling of Attention Drawing for Human-Robot Interaction
| Project/Area Number |
24700190
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | Chuo University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2012-04-01 – 2014-03-31
|
| Keywords | 注意誘導 / ヒューマンロボットインタラクション / 手品 |
|---|
| Research Abstract |
In order for robots to smoothly interact with humans, it is desirable that robots can manipulate human attention and behaviors. In this study, we developed a model of human visual attention for the manipulation of human attention based on an analysis of magic. We measured human gaze points while watching magic videos and compared them with the area where the magician intended to draw spectators' attention. The analysis showed that the relationship among the positions of the magician's face and hands and his gaze direction plays an important role in manipulating spectators' attention. On the basis of the analysis, we integrated a saliency map and a manipulation map that describes the relationship to develop a novel human attention model. The evaluation using the observed gaze points demonstrated that the proposed model can better explain human visual attention than the original saliency map.
|
