Motion to Text Based on Probabilistic Imitation Learning
| Project/Area Number |
24700188
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perception information processing/Intelligent robotics
|
|---|
| Research Institution | National Institute of Information and Communications Technology |
|---|
Principal Investigator |
SUGIURA Komei 独立行政法人情報通信研究機構, ユニバーサルコミュニケーション研究所情報利活用基盤研究室, 主任研究員 (60470473)
|
|---|
| Project Period (FY) |
2012-04-01 – 2015-03-31
|
| Project Status |
Completed (Fiscal Year 2014)
|
| Budget Amount *help |
¥4,420,000 (Direct Cost: ¥3,400,000、Indirect Cost: ¥1,020,000)
Fiscal Year 2014: ¥780,000 (Direct Cost: ¥600,000、Indirect Cost: ¥180,000)
Fiscal Year 2013: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2012: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
|
|---|
| Keywords | 模倣学習 / 知能ロボティクス / 機械学習 / 動作認識 / ヒューマンロボットインタラクション / 軌道生成 |
|---|
| Outline of Final Research Achievements |
Imitation learning has been paid much attention from the robotics and artificial intelligence communities. This project focuses on an online imitation learning method based on the maximum likelihood trajectories given by reference-point-dependent hidden Markov Models (RPD-HMMs). In the experiments, a user demonstrated the manipulation of objects so that the motion could be learned. The experimental results have shown that the proposed method decreases the average generation error in the trajectories. The proposed method is deployed on a service robot that generate learned motions through spoken dialogues.
|
Report
(4 results)
Research Products
(10 results)
