Matches in SemOpenAlex for { <https://semopenalex.org/work/W2626991471> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2626991471 abstract "To ensure system integrity, robots need to proactively avoid any unwanted physical perturbation that may cause damage to the underlying hardware. In this paper, we investigate a machine learning approach that allows robots to anticipate impending physical perturbations from perceptual cues. In contrast to other approaches that require knowledge about sources of perturbation to be encoded before deployment, our method is based on experiential learning. Robots learn to associate visual cues with subsequent physical perturbations and contacts. In turn, these extracted visual cues are then used to predict potential future perturbations acting on the robot. To this end, we introduce a novel deep network architecture which combines multiple sub-networks for dealing with robot dynamics and perceptual input from the environment. We present a self-supervised approach for training the system that does not require any labeling of training data. Extensive experiments in a human-robot interaction task show that a robot can learn to predict physical contact by a human interaction partner without any prior information or labeling." @default.
- W2626991471 created "2017-06-23" @default.
- W2626991471 creator A5024068845 @default.
- W2626991471 creator A5037356328 @default.
- W2626991471 date "2017-09-01" @default.
- W2626991471 modified "2023-09-23" @default.
- W2626991471 title "Robots that anticipate pain: Anticipating physical perturbations from visual cues through deep predictive models" @default.
- W2626991471 cites W1581800915 @default.
- W2626991471 cites W1844761640 @default.
- W2626991471 cites W1947481528 @default.
- W2626991471 cites W1981193003 @default.
- W2626991471 cites W2001316412 @default.
- W2626991471 cites W2012058822 @default.
- W2626991471 cites W2064675550 @default.
- W2626991471 cites W2095146110 @default.
- W2626991471 cites W2100300558 @default.
- W2626991471 cites W2102279668 @default.
- W2626991471 cites W2132991926 @default.
- W2626991471 cites W2149085596 @default.
- W2626991471 cites W2154777391 @default.
- W2626991471 cites W2157331557 @default.
- W2626991471 cites W2330788154 @default.
- W2626991471 cites W2418222507 @default.
- W2626991471 cites W2592008540 @default.
- W2626991471 doi "https://doi.org/10.1109/iros.2017.8206442" @default.
- W2626991471 hasPublicationYear "2017" @default.
- W2626991471 type Work @default.
- W2626991471 sameAs 2626991471 @default.
- W2626991471 citedByCount "5" @default.
- W2626991471 countsByYear W26269914712018 @default.
- W2626991471 countsByYear W26269914712019 @default.
- W2626991471 countsByYear W26269914712020 @default.
- W2626991471 countsByYear W26269914712022 @default.
- W2626991471 crossrefType "proceedings-article" @default.
- W2626991471 hasAuthorship W2626991471A5024068845 @default.
- W2626991471 hasAuthorship W2626991471A5037356328 @default.
- W2626991471 hasBestOaLocation W26269914712 @default.
- W2626991471 hasConcept C107457646 @default.
- W2626991471 hasConcept C111370547 @default.
- W2626991471 hasConcept C154945302 @default.
- W2626991471 hasConcept C31972630 @default.
- W2626991471 hasConcept C41008148 @default.
- W2626991471 hasConcept C90509273 @default.
- W2626991471 hasConceptScore W2626991471C107457646 @default.
- W2626991471 hasConceptScore W2626991471C111370547 @default.
- W2626991471 hasConceptScore W2626991471C154945302 @default.
- W2626991471 hasConceptScore W2626991471C31972630 @default.
- W2626991471 hasConceptScore W2626991471C41008148 @default.
- W2626991471 hasConceptScore W2626991471C90509273 @default.
- W2626991471 hasLocation W26269914711 @default.
- W2626991471 hasLocation W26269914712 @default.
- W2626991471 hasOpenAccess W2626991471 @default.
- W2626991471 hasPrimaryLocation W26269914711 @default.
- W2626991471 hasRelatedWork W1517376691 @default.
- W2626991471 hasRelatedWork W1526869945 @default.
- W2626991471 hasRelatedWork W1893841543 @default.
- W2626991471 hasRelatedWork W2021383747 @default.
- W2626991471 hasRelatedWork W2061090284 @default.
- W2626991471 hasRelatedWork W2125579716 @default.
- W2626991471 hasRelatedWork W2146536686 @default.
- W2626991471 hasRelatedWork W2604231787 @default.
- W2626991471 hasRelatedWork W4236636304 @default.
- W2626991471 hasRelatedWork W2510439428 @default.
- W2626991471 isParatext "false" @default.
- W2626991471 isRetracted "false" @default.
- W2626991471 magId "2626991471" @default.
- W2626991471 workType "article" @default.