DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Lee, Ju-Jang | - |
dc.contributor.advisor | 이주장 | - |
dc.contributor.author | Mao, Wentao | - |
dc.contributor.author | 모문탁 | - |
dc.date.accessioned | 2011-12-14T01:34:12Z | - |
dc.date.available | 2011-12-14T01:34:12Z | - |
dc.date.issued | 2010 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=419083&flag=dissertation | - |
dc.identifier.uri | http://hdl.handle.net/10203/36559 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기 및 전자공학과, 2010.2, [ viii, 58 p. ] | - |
dc.description.abstract | Research on biped humanoid robots is currently one of the most exciting topics in the field of robotics and among those issues, how to recover from the external push is typical one of the problems related to the robot stability. Different from the walking or other initiative motions, in push recovering, the humanoid has diffculties in taking actions in a short period when the unknown push occurs. Because of the complexity, in order to give a reference control to recover the robots from the push the more robust learning methods are needed. Moreover while imitating the human and animals, robots are preferred to learn the method in endless trials. Therefore the reinforcement learning (RL) is considered. In this thesis, a model for the push recovery is proposed as a reference trajectory. On the other hand, one of the reinforcement learning methods which is used in the continuous state and action space is introduced and applied to the push recovery with unknown push. Also, based on this RL method a with-model RL and a modified RL are proposed to realize the application of RL on the robot control. The results of the simulations are given to indicate the performance and are compared with each other to show the advantages of each method. | eng |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 넘어짐 방지 | - |
dc.subject | 인간형 로봇 | - |
dc.subject | 강화학습 | - |
dc.subject | reinforcement learning | - |
dc.subject | push recovery | - |
dc.subject | humanoid | - |
dc.title | Humanoid push recovery based on reinforcement learning in continuous state and action space | - |
dc.title.alternative | 연속 상태.행동공간에서 강화학습에 기반한 인간형 로봇의 넘어짐 방지 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 419083/325007 | - |
dc.description.department | 한국과학기술원 : 전기 및 전자공학과, | - |
dc.identifier.uid | 020083972 | - |
dc.contributor.localauthor | Lee, Ju-Jang | - |
dc.contributor.localauthor | 이주장 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.