Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104883169> ?p ?o ?g. }
Showing items 1 to 88 of
88
with 100 items per page.
- W3104883169 endingPage "2617" @default.
- W3104883169 startingPage "2610" @default.
- W3104883169 abstract "This paper presents a new learning framework that leverages the knowledge from imitation learning, deep reinforcement learning, and control theories to achieve human-style locomotion that is natural, dynamic, and robust for humanoids. We proposed novel approaches to introduce human bias, i.e. motion capture data and a special Multi-Expert network structure. We used the Multi-Expert network structure to smoothly blend behavioral features, and used the augmented reward design for the task and imitation rewards. Our reward design is composable, tunable, and explainable by using fundamental concepts from conventional humanoid control. We rigorously validated and benchmarked the learning framework which consistently produced robust locomotion behaviors in various test scenarios. Further, we demonstrated the capability of learning robust and versatile policies in the presence of disturbances, such as terrain irregularities and external pushes." @default.
- W3104883169 created "2020-11-23" @default.
- W3104883169 creator A5004106768 @default.
- W3104883169 creator A5006409524 @default.
- W3104883169 creator A5014324841 @default.
- W3104883169 creator A5019129514 @default.
- W3104883169 creator A5021393404 @default.
- W3104883169 date "2020-04-01" @default.
- W3104883169 modified "2023-10-18" @default.
- W3104883169 title "Learning Natural Locomotion Behaviors for Humanoid Robots Using Human Bias" @default.
- W3104883169 cites W2042533733 @default.
- W3104883169 cites W2051228319 @default.
- W3104883169 cites W2061227856 @default.
- W3104883169 cites W2103447784 @default.
- W3104883169 cites W2595365649 @default.
- W3104883169 cites W2611706523 @default.
- W3104883169 cites W2801567109 @default.
- W3104883169 cites W2885596080 @default.
- W3104883169 cites W2911087563 @default.
- W3104883169 cites W2967727187 @default.
- W3104883169 cites W3101808543 @default.
- W3104883169 cites W3106249594 @default.
- W3104883169 cites W4300892751 @default.
- W3104883169 doi "https://doi.org/10.1109/lra.2020.2972879" @default.
- W3104883169 hasPublicationYear "2020" @default.
- W3104883169 type Work @default.
- W3104883169 sameAs 3104883169 @default.
- W3104883169 citedByCount "28" @default.
- W3104883169 countsByYear W31048831692020 @default.
- W3104883169 countsByYear W31048831692021 @default.
- W3104883169 countsByYear W31048831692022 @default.
- W3104883169 countsByYear W31048831692023 @default.
- W3104883169 crossrefType "journal-article" @default.
- W3104883169 hasAuthorship W3104883169A5004106768 @default.
- W3104883169 hasAuthorship W3104883169A5006409524 @default.
- W3104883169 hasAuthorship W3104883169A5014324841 @default.
- W3104883169 hasAuthorship W3104883169A5019129514 @default.
- W3104883169 hasAuthorship W3104883169A5021393404 @default.
- W3104883169 hasBestOaLocation W31048831692 @default.
- W3104883169 hasConcept C107457646 @default.
- W3104883169 hasConcept C119857082 @default.
- W3104883169 hasConcept C126388530 @default.
- W3104883169 hasConcept C127413603 @default.
- W3104883169 hasConcept C154945302 @default.
- W3104883169 hasConcept C15744967 @default.
- W3104883169 hasConcept C201995342 @default.
- W3104883169 hasConcept C2780451532 @default.
- W3104883169 hasConcept C41008148 @default.
- W3104883169 hasConcept C60692881 @default.
- W3104883169 hasConcept C77805123 @default.
- W3104883169 hasConcept C90509273 @default.
- W3104883169 hasConcept C97541855 @default.
- W3104883169 hasConceptScore W3104883169C107457646 @default.
- W3104883169 hasConceptScore W3104883169C119857082 @default.
- W3104883169 hasConceptScore W3104883169C126388530 @default.
- W3104883169 hasConceptScore W3104883169C127413603 @default.
- W3104883169 hasConceptScore W3104883169C154945302 @default.
- W3104883169 hasConceptScore W3104883169C15744967 @default.
- W3104883169 hasConceptScore W3104883169C201995342 @default.
- W3104883169 hasConceptScore W3104883169C2780451532 @default.
- W3104883169 hasConceptScore W3104883169C41008148 @default.
- W3104883169 hasConceptScore W3104883169C60692881 @default.
- W3104883169 hasConceptScore W3104883169C77805123 @default.
- W3104883169 hasConceptScore W3104883169C90509273 @default.
- W3104883169 hasConceptScore W3104883169C97541855 @default.
- W3104883169 hasIssue "2" @default.
- W3104883169 hasLocation W31048831691 @default.
- W3104883169 hasLocation W31048831692 @default.
- W3104883169 hasLocation W31048831693 @default.
- W3104883169 hasOpenAccess W3104883169 @default.
- W3104883169 hasPrimaryLocation W31048831691 @default.
- W3104883169 hasRelatedWork W1804325819 @default.
- W3104883169 hasRelatedWork W2022224032 @default.
- W3104883169 hasRelatedWork W2031129854 @default.
- W3104883169 hasRelatedWork W2133659586 @default.
- W3104883169 hasRelatedWork W2166791242 @default.
- W3104883169 hasRelatedWork W2323122434 @default.
- W3104883169 hasRelatedWork W3038859464 @default.
- W3104883169 hasRelatedWork W4229726131 @default.
- W3104883169 hasRelatedWork W4319083788 @default.
- W3104883169 hasRelatedWork W4385626272 @default.
- W3104883169 hasVolume "5" @default.
- W3104883169 isParatext "false" @default.
- W3104883169 isRetracted "false" @default.
- W3104883169 magId "3104883169" @default.
- W3104883169 workType "article" @default.