Matches in SemOpenAlex for { <https://semopenalex.org/work/W2903932337> ?p ?o ?g. }
- W2903932337 endingPage "2107" @default.
- W2903932337 startingPage "2101" @default.
- W2903932337 abstract "Deep learning has the potential to have the impact on robot touch that it has had on robot vision. Optical tactile sensors act as a bridge between the subjects by allowing techniques from vision to be applied to touch. In this paper, we apply deep learning to an optical biomimetic tactile sensor, the TacTip, which images an array of papillae (pins) inside its sensing surface analogous to structures within human skin. Our main result is that the application of a deep CNN can give reliable edge perception and thus a robust policy for planning contact points to move around object contours. Robustness is demonstrated over several irregular and compliant objects with both tapping and continuous sliding, using a model trained only by tapping onto a disk. These results relied on using techniques to encourage generalization to tasks beyond which the model was trained. We expect this is a generic problem in practical applications of tactile sensing that deep learning will solve. A video demonstrating the approach can be found at https://www.youtube.com/watch?v=QHrGsG9AHts" @default.
- W2903932337 created "2018-12-22" @default.
- W2903932337 creator A5015897265 @default.
- W2903932337 creator A5025972235 @default.
- W2903932337 creator A5043903450 @default.
- W2903932337 creator A5053354197 @default.
- W2903932337 creator A5079415139 @default.
- W2903932337 date "2019-04-01" @default.
- W2903932337 modified "2023-10-01" @default.
- W2903932337 title "From Pixels to Percepts: Highly Robust Edge Perception and Contour Following Using Deep Learning and an Optical Biomimetic Tactile Sensor" @default.
- W2903932337 cites W102778925 @default.
- W2903932337 cites W1548071717 @default.
- W2903932337 cites W2026697682 @default.
- W2903932337 cites W2043899486 @default.
- W2903932337 cites W2062876937 @default.
- W2903932337 cites W2068882612 @default.
- W2903932337 cites W2069720069 @default.
- W2903932337 cites W2101779732 @default.
- W2903932337 cites W2113458228 @default.
- W2903932337 cites W2117292300 @default.
- W2903932337 cites W2200175238 @default.
- W2903932337 cites W2281770328 @default.
- W2903932337 cites W2293701398 @default.
- W2903932337 cites W2345650853 @default.
- W2903932337 cites W2397232755 @default.
- W2903932337 cites W2528124744 @default.
- W2903932337 cites W2567050476 @default.
- W2903932337 cites W2585610283 @default.
- W2903932337 cites W2587349145 @default.
- W2903932337 cites W2587761457 @default.
- W2903932337 cites W2607172324 @default.
- W2903932337 cites W2687523990 @default.
- W2903932337 cites W2775095556 @default.
- W2903932337 cites W2775635818 @default.
- W2903932337 cites W2781493652 @default.
- W2903932337 cites W2793447234 @default.
- W2903932337 cites W2804941773 @default.
- W2903932337 cites W2892010946 @default.
- W2903932337 cites W2962688712 @default.
- W2903932337 cites W2962693627 @default.
- W2903932337 cites W2963048676 @default.
- W2903932337 cites W2963915174 @default.
- W2903932337 cites W2964248288 @default.
- W2903932337 cites W2964295617 @default.
- W2903932337 cites W3099587965 @default.
- W2903932337 cites W3100674903 @default.
- W2903932337 cites W4246211341 @default.
- W2903932337 doi "https://doi.org/10.1109/lra.2019.2899192" @default.
- W2903932337 hasPublicationYear "2019" @default.
- W2903932337 type Work @default.
- W2903932337 sameAs 2903932337 @default.
- W2903932337 citedByCount "92" @default.
- W2903932337 countsByYear W29039323372019 @default.
- W2903932337 countsByYear W29039323372020 @default.
- W2903932337 countsByYear W29039323372021 @default.
- W2903932337 countsByYear W29039323372022 @default.
- W2903932337 countsByYear W29039323372023 @default.
- W2903932337 crossrefType "journal-article" @default.
- W2903932337 hasAuthorship W2903932337A5015897265 @default.
- W2903932337 hasAuthorship W2903932337A5025972235 @default.
- W2903932337 hasAuthorship W2903932337A5043903450 @default.
- W2903932337 hasAuthorship W2903932337A5053354197 @default.
- W2903932337 hasAuthorship W2903932337A5079415139 @default.
- W2903932337 hasBestOaLocation W29039323372 @default.
- W2903932337 hasConcept C104317684 @default.
- W2903932337 hasConcept C108583219 @default.
- W2903932337 hasConcept C134306372 @default.
- W2903932337 hasConcept C154945302 @default.
- W2903932337 hasConcept C160633673 @default.
- W2903932337 hasConcept C169760540 @default.
- W2903932337 hasConcept C177148314 @default.
- W2903932337 hasConcept C185592680 @default.
- W2903932337 hasConcept C26760741 @default.
- W2903932337 hasConcept C3017819093 @default.
- W2903932337 hasConcept C31972630 @default.
- W2903932337 hasConcept C33923547 @default.
- W2903932337 hasConcept C41008148 @default.
- W2903932337 hasConcept C46722567 @default.
- W2903932337 hasConcept C55493867 @default.
- W2903932337 hasConcept C63479239 @default.
- W2903932337 hasConcept C86803240 @default.
- W2903932337 hasConcept C90509273 @default.
- W2903932337 hasConceptScore W2903932337C104317684 @default.
- W2903932337 hasConceptScore W2903932337C108583219 @default.
- W2903932337 hasConceptScore W2903932337C134306372 @default.
- W2903932337 hasConceptScore W2903932337C154945302 @default.
- W2903932337 hasConceptScore W2903932337C160633673 @default.
- W2903932337 hasConceptScore W2903932337C169760540 @default.
- W2903932337 hasConceptScore W2903932337C177148314 @default.
- W2903932337 hasConceptScore W2903932337C185592680 @default.
- W2903932337 hasConceptScore W2903932337C26760741 @default.
- W2903932337 hasConceptScore W2903932337C3017819093 @default.
- W2903932337 hasConceptScore W2903932337C31972630 @default.
- W2903932337 hasConceptScore W2903932337C33923547 @default.
- W2903932337 hasConceptScore W2903932337C41008148 @default.
- W2903932337 hasConceptScore W2903932337C46722567 @default.
- W2903932337 hasConceptScore W2903932337C55493867 @default.
- W2903932337 hasConceptScore W2903932337C63479239 @default.