FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3003169307> ?p ?o ?g. }

• W3003169307 endingPage "2379" @default.
• W3003169307 startingPage "2372" @default.
• W3003169307 abstract "We demonstrate model-based, visual robot manipulation of deformable linear objects. Our approach is based on a state-space representation of the physical system that the robot aims to control. This choice has multiple advantages, including the ease of incorporating physics priors in the dynamics model and perception model, and the ease of planning manipulation actions. In addition, physical states can naturally represent object instances of different appearances. Therefore, dynamics in the state space can be learned in one setting and directly used in other visually different settings. This is in contrast to dynamics learned in pixel space or latent space, where generalization to visual differences are not guaranteed. Challenges in taking the state-space approach are the estimation of the high-dimensional state of a deformable object from raw images, where annotations are very expensive on real data, and finding a dynamics model that is both accurate, generalizable, and efficient to compute. We are the first to demonstrate self-supervised training of rope state estimation on real images, without requiring expensive annotations. This is achieved by our novel self-supervising learning objective, which is generalizable across a wide range of visual appearances. With estimated rope states, we train a fast and differentiable neural network dynamics model that encodes the physics of mass-spring systems. Our method has a higher accuracy in predicting future states compared to models that do not involve explicit state estimation and do not use any physics prior, while only using 3% of training data. We also show that our approach achieves more efficient manipulation, both in simulation and on a real robot, when used within a model predictive controller." @default.
• W3003169307 created "2020-02-07" @default.
• W3003169307 creator A5005314950 @default.
• W3003169307 creator A5015544619 @default.
• W3003169307 creator A5021676288 @default.
• W3003169307 creator A5071914915 @default.
• W3003169307 date "2020-04-01" @default.
• W3003169307 modified "2023-10-05" @default.
• W3003169307 title "Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects" @default.
• W3003169307 cites W1481925965 @default.
• W3003169307 cites W1995262563 @default.
• W3003169307 cites W2091344462 @default.
• W3003169307 cites W2096404799 @default.
• W3003169307 cites W2101073745 @default.
• W3003169307 cites W2138931081 @default.
• W3003169307 cites W2149355852 @default.
• W3003169307 cites W2206018105 @default.
• W3003169307 cites W2221845390 @default.
• W3003169307 cites W2410617946 @default.
• W3003169307 cites W2530616813 @default.
• W3003169307 cites W2567582053 @default.
• W3003169307 cites W2772044856 @default.
• W3003169307 cites W2798302325 @default.
• W3003169307 cites W2890290306 @default.
• W3003169307 cites W2902791462 @default.
• W3003169307 cites W2962871243 @default.
• W3003169307 cites W2964173765 @default.
• W3003169307 cites W2964254003 @default.
• W3003169307 cites W2966271811 @default.
• W3003169307 cites W2967246123 @default.
• W3003169307 doi "https://doi.org/10.1109/lra.2020.2969931" @default.
• W3003169307 hasPublicationYear "2020" @default.
• W3003169307 type Work @default.
• W3003169307 sameAs 3003169307 @default.
• W3003169307 citedByCount "85" @default.
• W3003169307 countsByYear W30031693072020 @default.
• W3003169307 countsByYear W30031693072021 @default.
• W3003169307 countsByYear W30031693072022 @default.
• W3003169307 countsByYear W30031693072023 @default.
• W3003169307 crossrefType "journal-article" @default.
• W3003169307 hasAuthorship W3003169307A5005314950 @default.
• W3003169307 hasAuthorship W3003169307A5015544619 @default.
• W3003169307 hasAuthorship W3003169307A5021676288 @default.
• W3003169307 hasAuthorship W3003169307A5071914915 @default.
• W3003169307 hasBestOaLocation W30031693072 @default.
• W3003169307 hasConcept C105795698 @default.
• W3003169307 hasConcept C11413529 @default.
• W3003169307 hasConcept C119857082 @default.
• W3003169307 hasConcept C134306372 @default.
• W3003169307 hasConcept C154945302 @default.
• W3003169307 hasConcept C162269090 @default.
• W3003169307 hasConcept C177148314 @default.
• W3003169307 hasConcept C17744445 @default.
• W3003169307 hasConcept C199539241 @default.
• W3003169307 hasConcept C2776359362 @default.
• W3003169307 hasConcept C2781238097 @default.
• W3003169307 hasConcept C31972630 @default.
• W3003169307 hasConcept C33923547 @default.
• W3003169307 hasConcept C41008148 @default.
• W3003169307 hasConcept C48103436 @default.
• W3003169307 hasConcept C72434380 @default.
• W3003169307 hasConcept C90509273 @default.
• W3003169307 hasConcept C94625758 @default.
• W3003169307 hasConceptScore W3003169307C105795698 @default.
• W3003169307 hasConceptScore W3003169307C11413529 @default.
• W3003169307 hasConceptScore W3003169307C119857082 @default.
• W3003169307 hasConceptScore W3003169307C134306372 @default.
• W3003169307 hasConceptScore W3003169307C154945302 @default.
• W3003169307 hasConceptScore W3003169307C162269090 @default.
• W3003169307 hasConceptScore W3003169307C177148314 @default.
• W3003169307 hasConceptScore W3003169307C17744445 @default.
• W3003169307 hasConceptScore W3003169307C199539241 @default.
• W3003169307 hasConceptScore W3003169307C2776359362 @default.
• W3003169307 hasConceptScore W3003169307C2781238097 @default.
• W3003169307 hasConceptScore W3003169307C31972630 @default.
• W3003169307 hasConceptScore W3003169307C33923547 @default.
• W3003169307 hasConceptScore W3003169307C41008148 @default.
• W3003169307 hasConceptScore W3003169307C48103436 @default.
• W3003169307 hasConceptScore W3003169307C72434380 @default.
• W3003169307 hasConceptScore W3003169307C90509273 @default.
• W3003169307 hasConceptScore W3003169307C94625758 @default.
• W3003169307 hasFunder F4320315934 @default.
• W3003169307 hasIssue "2" @default.
• W3003169307 hasLocation W30031693071 @default.
• W3003169307 hasLocation W30031693072 @default.
• W3003169307 hasOpenAccess W3003169307 @default.
• W3003169307 hasPrimaryLocation W30031693071 @default.
• W3003169307 hasRelatedWork W1837097281 @default.
• W3003169307 hasRelatedWork W1966410754 @default.
• W3003169307 hasRelatedWork W2007544051 @default.
• W3003169307 hasRelatedWork W2030539674 @default.
• W3003169307 hasRelatedWork W2095705906 @default.
• W3003169307 hasRelatedWork W2325242284 @default.
• W3003169307 hasRelatedWork W2363840281 @default.
• W3003169307 hasRelatedWork W2732308154 @default.
• W3003169307 hasRelatedWork W2789220062 @default.
• W3003169307 hasRelatedWork W2975200075 @default.
• W3003169307 hasVolume "5" @default.

• next