FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3010009603> ?p ?o ?g. }

• W3010009603 abstract "Robotic manipulation of deformable 1D objects such as ropes, cables, and hoses is challenging due to the lack of high-fidelity analytic models and large configuration spaces. Furthermore, learning end-to-end manipulation policies directly from images and physical interaction requires significant time on a robot and can fail to generalize across tasks. We address these challenges using interpretable deep visual representations for rope, extending recent work on dense object descriptors for robot manipulation. This facilitates the design of interpretable and transferable geometric policies built on top of the learned representations, decoupling visual reasoning and control. We present an approach that learns point-pair correspondences between initial and goal rope configurations, which implicitly encodes geometric structure, entirely in simulation from synthetic depth images. We demonstrate that the learned representation -- dense depth object descriptors (DDODs) -- can be used to manipulate a real rope into a variety of different arrangements either by learning from demonstrations or using interpretable geometric policies. In 50 trials of a knot-tying task with the ABB YuMi Robot, the system achieves a 66% knot-tying success rate from previously unseen configurations. See https://tinyurl.com/rope-learning for supplementary material and videos." @default.
• W3010009603 created "2020-03-13" @default.
• W3010009603 creator A5050342525 @default.
• W3010009603 creator A5052716347 @default.
• W3010009603 creator A5055891784 @default.
• W3010009603 creator A5070452999 @default.
• W3010009603 creator A5072427753 @default.
• W3010009603 creator A5075865569 @default.
• W3010009603 creator A5080000111 @default.
• W3010009603 date "2020-03-03" @default.
• W3010009603 modified "2023-10-16" @default.
• W3010009603 title "Learning Rope Manipulation Policies Using Dense Object Descriptors Trained on Synthetic Depth Data" @default.
• W3010009603 cites W1506053921 @default.
• W3010009603 cites W1938204631 @default.
• W3010009603 cites W1964502429 @default.
• W3010009603 cites W1971858902 @default.
• W3010009603 cites W1987017430 @default.
• W3010009603 cites W1990947293 @default.
• W3010009603 cites W1995414376 @default.
• W3010009603 cites W2018346149 @default.
• W3010009603 cites W2025468671 @default.
• W3010009603 cites W2058630951 @default.
• W3010009603 cites W2089630413 @default.
• W3010009603 cites W2099760513 @default.
• W3010009603 cites W2106097225 @default.
• W3010009603 cites W2120591602 @default.
• W3010009603 cites W2126998703 @default.
• W3010009603 cites W2138931081 @default.
• W3010009603 cites W2146447720 @default.
• W3010009603 cites W2151103935 @default.
• W3010009603 cites W2161969291 @default.
• W3010009603 cites W2336763592 @default.
• W3010009603 cites W2417563047 @default.
• W3010009603 cites W2472053385 @default.
• W3010009603 cites W2558625610 @default.
• W3010009603 cites W2736750746 @default.
• W3010009603 cites W2772168088 @default.
• W3010009603 cites W2904207885 @default.
• W3010009603 cites W2953249127 @default.
• W3010009603 cites W2962871243 @default.
• W3010009603 cites W2963003918 @default.
• W3010009603 cites W2963150697 @default.
• W3010009603 cites W2963666542 @default.
• W3010009603 cites W2964000117 @default.
• W3010009603 cites W2964021598 @default.
• W3010009603 cites W2964239605 @default.
• W3010009603 cites W2966271811 @default.
• W3010009603 cites W3009331570 @default.
• W3010009603 cites W3091905774 @default.
• W3010009603 doi "https://doi.org/10.48550/arxiv.2003.01835" @default.
• W3010009603 hasPublicationYear "2020" @default.
• W3010009603 type Work @default.
• W3010009603 sameAs 3010009603 @default.
• W3010009603 citedByCount "3" @default.
• W3010009603 countsByYear W30100096032020 @default.
• W3010009603 countsByYear W30100096032021 @default.
• W3010009603 crossrefType "posted-content" @default.
• W3010009603 hasAuthorship W3010009603A5050342525 @default.
• W3010009603 hasAuthorship W3010009603A5052716347 @default.
• W3010009603 hasAuthorship W3010009603A5055891784 @default.
• W3010009603 hasAuthorship W3010009603A5070452999 @default.
• W3010009603 hasAuthorship W3010009603A5072427753 @default.
• W3010009603 hasAuthorship W3010009603A5075865569 @default.
• W3010009603 hasAuthorship W3010009603A5080000111 @default.
• W3010009603 hasBestOaLocation W30100096031 @default.
• W3010009603 hasConcept C111919701 @default.
• W3010009603 hasConcept C113364801 @default.
• W3010009603 hasConcept C11413529 @default.
• W3010009603 hasConcept C119599485 @default.
• W3010009603 hasConcept C119857082 @default.
• W3010009603 hasConcept C127413603 @default.
• W3010009603 hasConcept C133731056 @default.
• W3010009603 hasConcept C154945302 @default.
• W3010009603 hasConcept C162269090 @default.
• W3010009603 hasConcept C17744445 @default.
• W3010009603 hasConcept C199539241 @default.
• W3010009603 hasConcept C205606062 @default.
• W3010009603 hasConcept C2776359362 @default.
• W3010009603 hasConcept C2776459999 @default.
• W3010009603 hasConcept C2780938662 @default.
• W3010009603 hasConcept C2781238097 @default.
• W3010009603 hasConcept C31972630 @default.
• W3010009603 hasConcept C41008148 @default.
• W3010009603 hasConcept C76155785 @default.
• W3010009603 hasConcept C90509273 @default.
• W3010009603 hasConcept C94625758 @default.
• W3010009603 hasConcept C97541855 @default.
• W3010009603 hasConceptScore W3010009603C111919701 @default.
• W3010009603 hasConceptScore W3010009603C113364801 @default.
• W3010009603 hasConceptScore W3010009603C11413529 @default.
• W3010009603 hasConceptScore W3010009603C119599485 @default.
• W3010009603 hasConceptScore W3010009603C119857082 @default.
• W3010009603 hasConceptScore W3010009603C127413603 @default.
• W3010009603 hasConceptScore W3010009603C133731056 @default.
• W3010009603 hasConceptScore W3010009603C154945302 @default.
• W3010009603 hasConceptScore W3010009603C162269090 @default.
• W3010009603 hasConceptScore W3010009603C17744445 @default.
• W3010009603 hasConceptScore W3010009603C199539241 @default.
• W3010009603 hasConceptScore W3010009603C205606062 @default.
• W3010009603 hasConceptScore W3010009603C2776359362 @default.

• next