Continuous Development of Robot Interactive Intelligence via Large Scale Human-in-the-Loop Social Simulation
| Project/Area Number |
24700199
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | The University of Tokyo (2013)
National Institute of Informatics (2012) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2012-04-01 – 2014-03-31
|
| Project Status |
Completed (Fiscal Year 2013)
|
| Budget Amount *help |
¥4,290,000 (Direct Cost: ¥3,300,000、Indirect Cost: ¥990,000)
Fiscal Year 2013: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2012: ¥2,470,000 (Direct Cost: ¥1,900,000、Indirect Cost: ¥570,000)
|
|---|
| Keywords | 知能ロボティックス / 人工知能 / シミュレーション工学 / バーチャルリアリティー / マルチモーダルインターフェース / 機械学習 / エージェント / 情報システム / 人口知能 / バーチャルリアリティ |
|---|
| Research Abstract |
The diversified research domains of human-robot interaction (HRI) have an issue of lacking common research practices and platform for collaboration. Furthermore, it is difficult and costly to conduct experiments with a large group of human subjects.
This work has proposed a development approach to model HRI by task analysis approach, where the interaction is decomposed into structured unit of tasks to represent the robot interactive intelligent model for operation and evaluation. The evaluation results can then feedback to improve the model. With this, the robot can achieve continuous improvement by having interaction with human subjects. Furthermore, a cloud-based human-in-the-loop social simulation system was developed to enable HRI simulation over a large group of human subjects. Based on the final prototype system, various HRI scenarios were developed to validate large scale HRI simulation and the continuous development of the robot interactive intelligence in this work.
|
Report
(3 results)
Research Products
(31 results)
