Project/Area Number |
16K21113
|
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
TAKEDA Seiji
SUYAMA Takashi
MATSUDA Takahiro
UENO Shunya
KARASAKI Junya
KUMANO So
MORIMOTO Toshinari
|
Project Period (FY) |
2016-04-01 – 2019-03-31
|
Project Status |
Completed (Fiscal Year 2018)
|
Budget Amount *help |
¥4,160,000 (Direct Cost: ¥3,200,000、Indirect Cost: ¥960,000)
Fiscal Year 2018: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2017: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2016: ¥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 / 内部状態推定 / マルチモーダルインターフェース / 志向姿勢 / 生理指標 / 相互適応 / インタラクションモデル / エージェント / インタラクション分析 |
Outline of Final Research Achievements |
We focused on Human Agent Interaction (HAI). We aimed to develop an interaction model in which humans think that the agent has the intention. For that purpose, we conducted experimental researches from two perspectives: Study 1) analysis of HAI sharing context between a human and an agent and Study 2) analysis of HAI with conflict and change of opinion in cooperative tasks. In Study 1, we suggested that the participants in this experimental study thought that the agent had the intention by forcedly performing cooperative and basic interactions in the same context. In Study 2, we suggested that HAI including multiple agents enabled the participants in this experimental study to efficiently build models of agent's behavior and recognition, and the participants thought that the agents have intentions in the cooperative task continuously. An experiment using agents with an interaction model that integrated these two findings showed that the human attitude at HAI improves implicitly.
|
Academic Significance and Societal Importance of the Research Achievements |
人工知能技術の発展により、知的な活動をするエージェント(例えば、仮想キャラクターやロボット)が増えている社会状況において、適切な人間側の認識や態度を誘発するインタラクションモデルを提案したことは、円滑なHAIを実現する上で有用な知見を与えたと言える。また、複数のエージェントとのHAIにおいて、エージェントの行動と認識のモデルの構築が1対1の場面よりも効果的に行われ、円滑なHAIの実現に有用なことを示したのは、エージェントを社会の中に位置づけるためのこれからの研究と検証に対して、示唆に富む結果を与えることができたと考えられる。
|