Matches in SemOpenAlex for { <https://semopenalex.org/work/W3213695441> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3213695441 endingPage "11267" @default.
- W3213695441 startingPage "11260" @default.
- W3213695441 abstract "When robots operate in human environments, it's critical that humans can quickly teach them new <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>concepts:</i> object-centric properties of the environment that they care about (e.g., objects <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>near</i> , <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>upright</i> , etc). However, teaching a new perceptual concept from high-dimensional robot sensor data (e.g., point clouds) is demanding, requiring an unrealistic amount of human labels. To address this, we propose a framework called Perceptual Concept Bootstrapping (PCB). First, we leverage the inherently lower-dimensional <italic xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>privileged information</i> , e.g., object poses and bounding boxes, available from a simulator only at training time to rapidly learn a low-dimensional, geometric concept from minimal human input. Second, we treat this low-dimensional concept as an automatic labeler to synthesize a large-scale high-dimensional data set with the simulator. With these two key ideas, PCB alleviates human label burden while still learning perceptual concepts that work with real sensor input where no privileged information is available. We evaluate PCB for learning spatial concepts that describe object state or multi-object relationships, and show it achieves superior performance compared to baseline methods. We also demonstrate the utility of the learned concepts in motion planning tasks on a 7-DoF Franka Panda robot." @default.
- W3213695441 created "2021-11-22" @default.
- W3213695441 creator A5014707300 @default.
- W3213695441 creator A5034978137 @default.
- W3213695441 creator A5044926286 @default.
- W3213695441 creator A5053446613 @default.
- W3213695441 creator A5053722464 @default.
- W3213695441 creator A5063086622 @default.
- W3213695441 creator A5067607006 @default.
- W3213695441 date "2022-10-01" @default.
- W3213695441 modified "2023-09-26" @default.
- W3213695441 title "Learning Perceptual Concepts by Bootstrapping From Human Queries" @default.
- W3213695441 cites W1999874108 @default.
- W3213695441 cites W2132083787 @default.
- W3213695441 cites W2141664020 @default.
- W3213695441 cites W2158582431 @default.
- W3213695441 cites W2594043679 @default.
- W3213695441 cites W2808201635 @default.
- W3213695441 cites W2895439318 @default.
- W3213695441 cites W2962951365 @default.
- W3213695441 cites W2963188159 @default.
- W3213695441 cites W2986303149 @default.
- W3213695441 cites W3038245394 @default.
- W3213695441 cites W3091340437 @default.
- W3213695441 cites W3091357794 @default.
- W3213695441 cites W3133557228 @default.
- W3213695441 cites W3179146632 @default.
- W3213695441 cites W3205994030 @default.
- W3213695441 cites W4225737910 @default.
- W3213695441 cites W4288076204 @default.
- W3213695441 cites W642078922 @default.
- W3213695441 doi "https://doi.org/10.1109/lra.2022.3196164" @default.
- W3213695441 hasPublicationYear "2022" @default.
- W3213695441 type Work @default.
- W3213695441 sameAs 3213695441 @default.
- W3213695441 citedByCount "2" @default.
- W3213695441 countsByYear W32136954412023 @default.
- W3213695441 crossrefType "journal-article" @default.
- W3213695441 hasAuthorship W3213695441A5014707300 @default.
- W3213695441 hasAuthorship W3213695441A5034978137 @default.
- W3213695441 hasAuthorship W3213695441A5044926286 @default.
- W3213695441 hasAuthorship W3213695441A5053446613 @default.
- W3213695441 hasAuthorship W3213695441A5053722464 @default.
- W3213695441 hasAuthorship W3213695441A5063086622 @default.
- W3213695441 hasAuthorship W3213695441A5067607006 @default.
- W3213695441 hasBestOaLocation W32136954412 @default.
- W3213695441 hasConcept C115961682 @default.
- W3213695441 hasConcept C119857082 @default.
- W3213695441 hasConcept C147037132 @default.
- W3213695441 hasConcept C149782125 @default.
- W3213695441 hasConcept C153083717 @default.
- W3213695441 hasConcept C154945302 @default.
- W3213695441 hasConcept C15744967 @default.
- W3213695441 hasConcept C169760540 @default.
- W3213695441 hasConcept C177264268 @default.
- W3213695441 hasConcept C199360897 @default.
- W3213695441 hasConcept C207609745 @default.
- W3213695441 hasConcept C26760741 @default.
- W3213695441 hasConcept C2781238097 @default.
- W3213695441 hasConcept C33923547 @default.
- W3213695441 hasConcept C41008148 @default.
- W3213695441 hasConceptScore W3213695441C115961682 @default.
- W3213695441 hasConceptScore W3213695441C119857082 @default.
- W3213695441 hasConceptScore W3213695441C147037132 @default.
- W3213695441 hasConceptScore W3213695441C149782125 @default.
- W3213695441 hasConceptScore W3213695441C153083717 @default.
- W3213695441 hasConceptScore W3213695441C154945302 @default.
- W3213695441 hasConceptScore W3213695441C15744967 @default.
- W3213695441 hasConceptScore W3213695441C169760540 @default.
- W3213695441 hasConceptScore W3213695441C177264268 @default.
- W3213695441 hasConceptScore W3213695441C199360897 @default.
- W3213695441 hasConceptScore W3213695441C207609745 @default.
- W3213695441 hasConceptScore W3213695441C26760741 @default.
- W3213695441 hasConceptScore W3213695441C2781238097 @default.
- W3213695441 hasConceptScore W3213695441C33923547 @default.
- W3213695441 hasConceptScore W3213695441C41008148 @default.
- W3213695441 hasIssue "4" @default.
- W3213695441 hasLocation W32136954411 @default.
- W3213695441 hasLocation W32136954412 @default.
- W3213695441 hasOpenAccess W3213695441 @default.
- W3213695441 hasPrimaryLocation W32136954411 @default.
- W3213695441 hasRelatedWork W2002995732 @default.
- W3213695441 hasRelatedWork W2068931720 @default.
- W3213695441 hasRelatedWork W2756241593 @default.
- W3213695441 hasRelatedWork W2801801420 @default.
- W3213695441 hasRelatedWork W3011810433 @default.
- W3213695441 hasRelatedWork W3090948685 @default.
- W3213695441 hasRelatedWork W4307244142 @default.
- W3213695441 hasRelatedWork W4311828510 @default.
- W3213695441 hasRelatedWork W4312050762 @default.
- W3213695441 hasRelatedWork W4362697683 @default.
- W3213695441 hasVolume "7" @default.
- W3213695441 isParatext "false" @default.
- W3213695441 isRetracted "false" @default.
- W3213695441 magId "3213695441" @default.
- W3213695441 workType "article" @default.