Matches in SemOpenAlex for { <https://semopenalex.org/work/W3036844037> ?p ?o ?g. }
Showing items 1 to 84 of
84
with 100 items per page.
- W3036844037 abstract "This paper tackles the challenge of predicting grasp failures in soft hands before they happen, by combining deep learning with a sensing strategy based on distributed Inertial Measurement Units. We propose two neural architectures, which we implemented and tested with an articulated soft hand - the Pisa/IIT SoftHand - and a continuously deformable soft hand - the RBO Hand. The first architecture (Classifier) implements a-posteriori detection of the failure event, serving as a test-bench to assess the possibility of extracting failure information from the discussed input signals. This network reaches up to 100% of accuracy within our experimental validation. Motivated by these results, we introduce a second architecture (Predictor), which is the main contribution of the paper. This network works on-line and takes as input a multidimensional continuum stream of raw signals coming from the Inertial Measurement Units. The network is trained to predict the occurrence in the near future of a failure event. The Predictor detects 100% of failures with both hands, with the detection happening on average 1.96 seconds before the actual failing occurs - leaving plenty of time to an hypothetical controller to react." @default.
- W3036844037 created "2020-06-25" @default.
- W3036844037 creator A5004273214 @default.
- W3036844037 creator A5037157112 @default.
- W3036844037 creator A5039518808 @default.
- W3036844037 creator A5050239145 @default.
- W3036844037 creator A5050576327 @default.
- W3036844037 creator A5056194661 @default.
- W3036844037 creator A5066830185 @default.
- W3036844037 date "2020-05-01" @default.
- W3036844037 modified "2023-09-23" @default.
- W3036844037 title "To grasp or not to grasp: an end-to-end deep-learning approach for predicting grasping failures in soft hands" @default.
- W3036844037 cites W1596717185 @default.
- W3036844037 cites W1888892744 @default.
- W3036844037 cites W2064675550 @default.
- W3036844037 cites W2123951871 @default.
- W3036844037 cites W2125283600 @default.
- W3036844037 cites W2151831732 @default.
- W3036844037 cites W2201912979 @default.
- W3036844037 cites W2323956509 @default.
- W3036844037 cites W2410441310 @default.
- W3036844037 cites W2416743726 @default.
- W3036844037 cites W2556078315 @default.
- W3036844037 cites W2588211988 @default.
- W3036844037 cites W2772523001 @default.
- W3036844037 cites W2784648116 @default.
- W3036844037 cites W2789805345 @default.
- W3036844037 cites W2793400769 @default.
- W3036844037 cites W2897005597 @default.
- W3036844037 cites W2909176668 @default.
- W3036844037 cites W2911386938 @default.
- W3036844037 cites W2913446864 @default.
- W3036844037 cites W2913919845 @default.
- W3036844037 cites W2943200793 @default.
- W3036844037 cites W2947323496 @default.
- W3036844037 cites W3011904522 @default.
- W3036844037 cites W971303027 @default.
- W3036844037 doi "https://doi.org/10.1109/robosoft48309.2020.9116041" @default.
- W3036844037 hasPublicationYear "2020" @default.
- W3036844037 type Work @default.
- W3036844037 sameAs 3036844037 @default.
- W3036844037 citedByCount "5" @default.
- W3036844037 countsByYear W30368440372021 @default.
- W3036844037 countsByYear W30368440372022 @default.
- W3036844037 crossrefType "proceedings-article" @default.
- W3036844037 hasAuthorship W3036844037A5004273214 @default.
- W3036844037 hasAuthorship W3036844037A5037157112 @default.
- W3036844037 hasAuthorship W3036844037A5039518808 @default.
- W3036844037 hasAuthorship W3036844037A5050239145 @default.
- W3036844037 hasAuthorship W3036844037A5050576327 @default.
- W3036844037 hasAuthorship W3036844037A5056194661 @default.
- W3036844037 hasAuthorship W3036844037A5066830185 @default.
- W3036844037 hasBestOaLocation W30368440372 @default.
- W3036844037 hasConcept C107457646 @default.
- W3036844037 hasConcept C115903868 @default.
- W3036844037 hasConcept C154945302 @default.
- W3036844037 hasConcept C171268870 @default.
- W3036844037 hasConcept C41008148 @default.
- W3036844037 hasConcept C74296488 @default.
- W3036844037 hasConceptScore W3036844037C107457646 @default.
- W3036844037 hasConceptScore W3036844037C115903868 @default.
- W3036844037 hasConceptScore W3036844037C154945302 @default.
- W3036844037 hasConceptScore W3036844037C171268870 @default.
- W3036844037 hasConceptScore W3036844037C41008148 @default.
- W3036844037 hasConceptScore W3036844037C74296488 @default.
- W3036844037 hasLocation W30368440371 @default.
- W3036844037 hasLocation W30368440372 @default.
- W3036844037 hasLocation W30368440373 @default.
- W3036844037 hasOpenAccess W3036844037 @default.
- W3036844037 hasPrimaryLocation W30368440371 @default.
- W3036844037 hasRelatedWork W1969495992 @default.
- W3036844037 hasRelatedWork W2557924869 @default.
- W3036844037 hasRelatedWork W2888481972 @default.
- W3036844037 hasRelatedWork W2888922990 @default.
- W3036844037 hasRelatedWork W3004284873 @default.
- W3036844037 hasRelatedWork W3022468211 @default.
- W3036844037 hasRelatedWork W3192511943 @default.
- W3036844037 hasRelatedWork W3214506804 @default.
- W3036844037 hasRelatedWork W4200303201 @default.
- W3036844037 hasRelatedWork W4206619538 @default.
- W3036844037 isParatext "false" @default.
- W3036844037 isRetracted "false" @default.
- W3036844037 magId "3036844037" @default.
- W3036844037 workType "article" @default.