2004年
Motion recognition by combining HMM and reinforcement learning
2004 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN & CYBERNETICS, VOLS 1-7
- ,
- ,
- 開始ページ
- 5259
- 終了ページ
- 5264
- 記述言語
- 英語
- 掲載種別
- DOI
- 10.1109/ICSMC.2004.1401029
- 出版者・発行元
- IEEE
It is difficult to give a robot all possible motions beforehand in a certain environment. Therefore, the robot needs to learn how to recognize others' motions and to generate its own motions autonomously for working well. These learning algorithms need an efficient way to make recognition and generation of motions work together, because the), take many computing resources. This paper focuses on a generation-based recognition.
Our system consists of recognition and generation modules. The former and latter are constructed from left-to-right Hidden Markov Models (HMM) and Reinforcement Learning (RL), respectively. When a HMM in recognition module does not work enough, the model parameters of HMM are re-estimated by using a state-value function of RL in generation module. The proposed method enables us to improve the reliability of the HMM.
Our system consists of recognition and generation modules. The former and latter are constructed from left-to-right Hidden Markov Models (HMM) and Reinforcement Learning (RL), respectively. When a HMM in recognition module does not work enough, the model parameters of HMM are re-estimated by using a state-value function of RL in generation module. The proposed method enables us to improve the reliability of the HMM.
- リンク情報
- ID情報
-
- DOI : 10.1109/ICSMC.2004.1401029
- ISSN : 1062-922X
- Web of Science ID : WOS:000226863300885