Development and evaluation of methods to mutually estimate emphasizing points in interaction tasks
| Project/Area Number |
25870353
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Human interface and interaction
Intelligent informatics
|
|---|
| Research Institution | Kyoto University |
|---|
Principal Investigator |
|
|---|
| Research Collaborator |
NISHIDA Toyoaki
SUTOU Satsuki
AKITOMO Shinya
KATAOKA Misao
FURUTANI Jun
SASAKURA Takashi
HORII Soushi
SUYAMA Takashi
MATSUMOTO Asami
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2015: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | ヒューマンエージェントインタラクション / 意図推定 / 志向姿勢 / 共同意図構築 / マルチモーダルインターフェース / インタラクション分析 / インタラクションモデル / 視座協創 |
|---|
| Outline of Final Research Achievements |
We proposed methods for smooth human-agent interaction based on mutual respect in passive and active interaction situations. In the passive interaction situations, we proposed methods to induce intentions to examine an agent's proposals about tasks in decision-making. In the methods, we dynamically estimated emphasizing points for the decision-making using verbal and nonverbal information. In the active interaction situations, we proposed a model of alternating propagation of global purposes and local objectives by a two-layered network-connected emphasizing factors. In addition, we found that "intentional stance" was important to realize smooth human-agent interaction. Therefore, we investigated how to induce the intentional stance and prototyped an agent which was integrated our interaction methods and models. On the whole, we can suggest human-agent interaction methods and models to understand intentions of humans and agents through the interaction process.
|
Report
(4 results)
Research Products
(13 results)
