• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2014 Fiscal Year Final Research Report

Motion to Text Based on Probabilistic Imitation Learning

Research Project

  • PDF
Project/Area Number 24700188
Research Category

Grant-in-Aid for Young Scientists (B)

Allocation TypeMulti-year Fund
Research Field Perception information processing/Intelligent robotics
Research InstitutionNational 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
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.

Free Research Field

ロボット対話

URL: 

Published: 2016-06-03  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi