Matches in SemOpenAlex for { <https://semopenalex.org/work/W3104303755> ?p ?o ?g. }
- W3104303755 abstract "Blending representation learning approaches with simultaneous localization and mapping (SLAM) systems is an open question, because of their highly modular and complex nature. Functionally, SLAM is an operation that transforms raw sensor inputs into a distribution over the state(s) of the robot and the environment. If this transformation (SLAM) were expressible as a differentiable function, we could leverage task-based error signals to learn representations that optimize task performance. However, several components of a typical dense SLAM system are non-differentiable. In this work, we propose gradSLAM, a methodology for posing SLAM systems as differentiable computational graphs, which unifies gradient-based learning and SLAM. We propose differentiable trust-region optimizers, surface measurement and fusion schemes, and raycasting, without sacrificing accuracy. This amalgamation of dense SLAM with computational graphs enables us to backprop all the way from 3D maps to 2D pixels, opening up new possibilities in gradient-based learning for SLAM. TL;DR: We leverage the power of automatic differentiation frameworks to make dense SLAM differentiable." @default.
- W3104303755 created "2020-11-23" @default.
- W3104303755 creator A5021709131 @default.
- W3104303755 creator A5037065865 @default.
- W3104303755 creator A5047370393 @default.
- W3104303755 creator A5061646570 @default.
- W3104303755 date "2019-10-23" @default.
- W3104303755 modified "2023-09-23" @default.
- W3104303755 title "gradSLAM: Automagically differentiable SLAM" @default.
- W3104303755 cites W1987648924 @default.
- W3104303755 cites W2009422376 @default.
- W3104303755 cites W2016285927 @default.
- W3104303755 cites W2021851106 @default.
- W3104303755 cites W2021930164 @default.
- W3104303755 cites W2058535340 @default.
- W3104303755 cites W2064675550 @default.
- W3104303755 cites W2065906272 @default.
- W3104303755 cites W2091226544 @default.
- W3104303755 cites W2105471083 @default.
- W3104303755 cites W2114123573 @default.
- W3104303755 cites W2118877769 @default.
- W3104303755 cites W2126053368 @default.
- W3104303755 cites W2143769815 @default.
- W3104303755 cites W2163605009 @default.
- W3104303755 cites W2184045248 @default.
- W3104303755 cites W2200124539 @default.
- W3104303755 cites W2300779272 @default.
- W3104303755 cites W2336961836 @default.
- W3104303755 cites W2489710028 @default.
- W3104303755 cites W2594519801 @default.
- W3104303755 cites W2606794968 @default.
- W3104303755 cites W2887825894 @default.
- W3104303755 cites W2889827408 @default.
- W3104303755 cites W2906346536 @default.
- W3104303755 cites W2914238185 @default.
- W3104303755 cites W2941394598 @default.
- W3104303755 cites W2962958942 @default.
- W3104303755 cites W2963091090 @default.
- W3104303755 cites W2963403868 @default.
- W3104303755 cites W2963453931 @default.
- W3104303755 cites W2963706662 @default.
- W3104303755 cites W2963739349 @default.
- W3104303755 cites W2963970238 @default.
- W3104303755 cites W2964233911 @default.
- W3104303755 cites W2964314455 @default.
- W3104303755 cites W2965621489 @default.
- W3104303755 cites W2971278627 @default.
- W3104303755 cites W2978409868 @default.
- W3104303755 cites W2980925180 @default.
- W3104303755 cites W3025573667 @default.
- W3104303755 cites W3098467253 @default.
- W3104303755 cites W603908379 @default.
- W3104303755 hasPublicationYear "2019" @default.
- W3104303755 type Work @default.
- W3104303755 sameAs 3104303755 @default.
- W3104303755 citedByCount "3" @default.
- W3104303755 countsByYear W31043037552020 @default.
- W3104303755 countsByYear W31043037552021 @default.
- W3104303755 crossrefType "posted-content" @default.
- W3104303755 hasAuthorship W3104303755A5021709131 @default.
- W3104303755 hasAuthorship W3104303755A5037065865 @default.
- W3104303755 hasAuthorship W3104303755A5047370393 @default.
- W3104303755 hasAuthorship W3104303755A5061646570 @default.
- W3104303755 hasConcept C101468663 @default.
- W3104303755 hasConcept C111919701 @default.
- W3104303755 hasConcept C11413529 @default.
- W3104303755 hasConcept C153083717 @default.
- W3104303755 hasConcept C154945302 @default.
- W3104303755 hasConcept C17744445 @default.
- W3104303755 hasConcept C199539241 @default.
- W3104303755 hasConcept C19966478 @default.
- W3104303755 hasConcept C202444582 @default.
- W3104303755 hasConcept C202615002 @default.
- W3104303755 hasConcept C2776359362 @default.
- W3104303755 hasConcept C31972630 @default.
- W3104303755 hasConcept C33923547 @default.
- W3104303755 hasConcept C41008148 @default.
- W3104303755 hasConcept C86369673 @default.
- W3104303755 hasConcept C90509273 @default.
- W3104303755 hasConcept C94625758 @default.
- W3104303755 hasConceptScore W3104303755C101468663 @default.
- W3104303755 hasConceptScore W3104303755C111919701 @default.
- W3104303755 hasConceptScore W3104303755C11413529 @default.
- W3104303755 hasConceptScore W3104303755C153083717 @default.
- W3104303755 hasConceptScore W3104303755C154945302 @default.
- W3104303755 hasConceptScore W3104303755C17744445 @default.
- W3104303755 hasConceptScore W3104303755C199539241 @default.
- W3104303755 hasConceptScore W3104303755C19966478 @default.
- W3104303755 hasConceptScore W3104303755C202444582 @default.
- W3104303755 hasConceptScore W3104303755C202615002 @default.
- W3104303755 hasConceptScore W3104303755C2776359362 @default.
- W3104303755 hasConceptScore W3104303755C31972630 @default.
- W3104303755 hasConceptScore W3104303755C33923547 @default.
- W3104303755 hasConceptScore W3104303755C41008148 @default.
- W3104303755 hasConceptScore W3104303755C86369673 @default.
- W3104303755 hasConceptScore W3104303755C90509273 @default.
- W3104303755 hasConceptScore W3104303755C94625758 @default.
- W3104303755 hasLocation W31043037551 @default.
- W3104303755 hasOpenAccess W3104303755 @default.
- W3104303755 hasPrimaryLocation W31043037551 @default.