DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Hwangbo, Jemin | - |
dc.contributor.advisor | 황보제민 | - |
dc.contributor.author | 흐첼 야콥 | - |
dc.date.accessioned | 2023-06-22T19:30:57Z | - |
dc.date.available | 2023-06-22T19:30:57Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1032299&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/308137 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 기계공학과, 2023.2,[viii, 68 p. :] | - |
dc.description.abstract | This thesis presents a way to solve the issue of a jump with a run-up over an obstacle using a quadruped robot. To be applicable in reality, the ability to run on flat terrain should not be degraded. For this purpose, a hierarchical framework with two neural networks is used in this work. Both networks are trained using reinforcement learning. The switch between the two networks is done based on the distance between the robot and the hurdle. Simulations show a high success rate for the developed policy. The possibility to transfer this approach to reality is proven by an experiment on a real robot. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Legged robots▼aReinforcement learning▼aQuadruped robots | - |
dc.subject | 보행로봇▼a강화학습▼a사족로봇 | - |
dc.title | Learning to jump over a hurdle with a quadruped robot using reinforcement learning | - |
dc.title.alternative | 강화학습을 이용한 사족보행로봇의 장애물 뛰어넘기 학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :기계공학과, | - |
dc.contributor.alternativeauthor | Jakob Hötzel | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.