Matches in SemOpenAlex for { <https://semopenalex.org/work/W3089793705> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W3089793705 abstract "This paper introduces Action Image, a new grasp proposal representation that allows learning an end-to-end deep-grasping policy. Our model achieves 84% grasp success on 172 real world objects while being trained only in simulation on 48 objects with just naive domain randomization. Similar to computer vision problems, such as object detection, Action Image builds on the idea that object features are invariant to translation in image space. Therefore, grasp quality is invariant when evaluating the object-gripper relationship; a successful grasp for an object depends on its local context, but is independent of the surrounding environment. Action Image represents a grasp proposal as an image and uses a deep convolutional network to infer grasp quality. We show that by using an Action Image representation, trained networks are able to extract local, salient features of grasping tasks that generalize across different objects and environments. We show that this representation works on a variety of inputs, including color images (RGB), depth images (D), and combined color-depth (RGB-D). Our experimental results demonstrate that networks utilizing an Action Image representation exhibit strong domain transfer between training on simulated data and inference on real-world sensor streams. Finally, our experiments show that a network trained with Action Image improves grasp success (84% vs. 53%) over a baseline model with the same structure, but using actions encoded as vectors." @default.
- W3089793705 created "2020-10-08" @default.
- W3089793705 creator A5037464692 @default.
- W3089793705 creator A5039293409 @default.
- W3089793705 creator A5065802887 @default.
- W3089793705 creator A5076509678 @default.
- W3089793705 creator A5080415080 @default.
- W3089793705 date "2020-05-01" @default.
- W3089793705 modified "2023-09-23" @default.
- W3089793705 title "Action Image Representation: Learning Scalable Deep Grasping Policies with Zero Real World Data" @default.
- W3089793705 cites W1503925285 @default.
- W3089793705 cites W1577352482 @default.
- W3089793705 cites W1820657498 @default.
- W3089793705 cites W1986533639 @default.
- W3089793705 cites W1999156278 @default.
- W3089793705 cites W2064878003 @default.
- W3089793705 cites W2085949256 @default.
- W3089793705 cites W2161047498 @default.
- W3089793705 cites W2201912979 @default.
- W3089793705 cites W2205950488 @default.
- W3089793705 cites W2561523096 @default.
- W3089793705 cites W2577484822 @default.
- W3089793705 cites W2605102758 @default.
- W3089793705 cites W2962736495 @default.
- W3089793705 cites W2962746398 @default.
- W3089793705 cites W2962899390 @default.
- W3089793705 cites W2963276406 @default.
- W3089793705 cites W2967842640 @default.
- W3089793705 cites W3112422759 @default.
- W3089793705 cites W70651934 @default.
- W3089793705 doi "https://doi.org/10.1109/icra40945.2020.9197415" @default.
- W3089793705 hasPublicationYear "2020" @default.
- W3089793705 type Work @default.
- W3089793705 sameAs 3089793705 @default.
- W3089793705 citedByCount "13" @default.
- W3089793705 countsByYear W30897937052020 @default.
- W3089793705 countsByYear W30897937052021 @default.
- W3089793705 countsByYear W30897937052022 @default.
- W3089793705 countsByYear W30897937052023 @default.
- W3089793705 crossrefType "proceedings-article" @default.
- W3089793705 hasAuthorship W3089793705A5037464692 @default.
- W3089793705 hasAuthorship W3089793705A5039293409 @default.
- W3089793705 hasAuthorship W3089793705A5065802887 @default.
- W3089793705 hasAuthorship W3089793705A5076509678 @default.
- W3089793705 hasAuthorship W3089793705A5080415080 @default.
- W3089793705 hasBestOaLocation W30897937052 @default.
- W3089793705 hasConcept C115961682 @default.
- W3089793705 hasConcept C153180895 @default.
- W3089793705 hasConcept C154945302 @default.
- W3089793705 hasConcept C171268870 @default.
- W3089793705 hasConcept C17744445 @default.
- W3089793705 hasConcept C199360897 @default.
- W3089793705 hasConcept C199539241 @default.
- W3089793705 hasConcept C2776214188 @default.
- W3089793705 hasConcept C2776359362 @default.
- W3089793705 hasConcept C2779757391 @default.
- W3089793705 hasConcept C2781238097 @default.
- W3089793705 hasConcept C31972630 @default.
- W3089793705 hasConcept C41008148 @default.
- W3089793705 hasConcept C81363708 @default.
- W3089793705 hasConcept C82990744 @default.
- W3089793705 hasConcept C94625758 @default.
- W3089793705 hasConceptScore W3089793705C115961682 @default.
- W3089793705 hasConceptScore W3089793705C153180895 @default.
- W3089793705 hasConceptScore W3089793705C154945302 @default.
- W3089793705 hasConceptScore W3089793705C171268870 @default.
- W3089793705 hasConceptScore W3089793705C17744445 @default.
- W3089793705 hasConceptScore W3089793705C199360897 @default.
- W3089793705 hasConceptScore W3089793705C199539241 @default.
- W3089793705 hasConceptScore W3089793705C2776214188 @default.
- W3089793705 hasConceptScore W3089793705C2776359362 @default.
- W3089793705 hasConceptScore W3089793705C2779757391 @default.
- W3089793705 hasConceptScore W3089793705C2781238097 @default.
- W3089793705 hasConceptScore W3089793705C31972630 @default.
- W3089793705 hasConceptScore W3089793705C41008148 @default.
- W3089793705 hasConceptScore W3089793705C81363708 @default.
- W3089793705 hasConceptScore W3089793705C82990744 @default.
- W3089793705 hasConceptScore W3089793705C94625758 @default.
- W3089793705 hasLocation W30897937051 @default.
- W3089793705 hasLocation W30897937052 @default.
- W3089793705 hasOpenAccess W3089793705 @default.
- W3089793705 hasPrimaryLocation W30897937051 @default.
- W3089793705 hasRelatedWork W1561942766 @default.
- W3089793705 hasRelatedWork W2101128524 @default.
- W3089793705 hasRelatedWork W2557924869 @default.
- W3089793705 hasRelatedWork W2768774443 @default.
- W3089793705 hasRelatedWork W2940661641 @default.
- W3089793705 hasRelatedWork W3004284873 @default.
- W3089793705 hasRelatedWork W3185561939 @default.
- W3089793705 hasRelatedWork W4249963983 @default.
- W3089793705 hasRelatedWork W4287903832 @default.
- W3089793705 hasRelatedWork W4320809347 @default.
- W3089793705 isParatext "false" @default.
- W3089793705 isRetracted "false" @default.
- W3089793705 magId "3089793705" @default.
- W3089793705 workType "article" @default.