Matches in SemOpenAlex for { <https://semopenalex.org/work/W2973454014> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W2973454014 abstract "Author(s): Tobin, Joshua P | Advisor(s): Abbeel, Pieter | Abstract: Modern deep learning techniques are data-hungry, which presents a problem in robotics because real-world robotic data is difficult to collect. Simulated data is cheap and scalable, but jumping the to use simulated data for real-world tasks is challenging. In this thesis, we discuss using synthetic data to learn visual models that allow robots to perform manipulation tasks in the real world. We begin by discussing domain randomization, a technique for bridging the reality gap by massively randomizing the visual properties of the simulator. We demonstrate that, using domain randomization, synthetic data alone can be used to train a deep neural network to localize objects accurately enough for a robot to grasp them in the real world. The remainder of the thesis discusses extensions of this approach to a broader range of objects and scenes. First, we introduce a data generation pipeline inspired by the success of domain randomization for visual data that creates millions of unrealistic procedurally generated random objects, removing the assumption that 3D models of the objects are present at training time. Second, we reformulate the problem from pose prediction to grasp prediction and introduce a generative model architecture that learns a distribution over grasps, allowing our models to handle pose ambiguity and grasp a wide range of objects with a single neural network. Third, we introduce an attention mechanism for 3-dimensional data. We demonstrate that this attention mechanism can be used to perform higher fidelity neural rendering, and that models learned this way can be fine-tuned to perform accurate pose estimation when the camera intrinsics are unknown at training time.We conclude by surveying recent applications and extensions of domain randomization in the literature and suggesting several promising directions for research in sim-to-real transfer for robotics." @default.
- W2973454014 created "2019-09-26" @default.
- W2973454014 creator A5012812463 @default.
- W2973454014 date "2019-01-01" @default.
- W2973454014 modified "2023-09-24" @default.
- W2973454014 title "Real-World Robotic Perception and Control Using Synthetic Data" @default.
- W2973454014 hasPublicationYear "2019" @default.
- W2973454014 type Work @default.
- W2973454014 sameAs 2973454014 @default.
- W2973454014 citedByCount "1" @default.
- W2973454014 countsByYear W29734540142021 @default.
- W2973454014 crossrefType "journal-article" @default.
- W2973454014 hasAuthorship W2973454014A5012812463 @default.
- W2973454014 hasConcept C108583219 @default.
- W2973454014 hasConcept C119857082 @default.
- W2973454014 hasConcept C154945302 @default.
- W2973454014 hasConcept C160920958 @default.
- W2973454014 hasConcept C171268870 @default.
- W2973454014 hasConcept C199360897 @default.
- W2973454014 hasConcept C205711294 @default.
- W2973454014 hasConcept C31972630 @default.
- W2973454014 hasConcept C34413123 @default.
- W2973454014 hasConcept C41008148 @default.
- W2973454014 hasConcept C48044578 @default.
- W2973454014 hasConcept C50644808 @default.
- W2973454014 hasConcept C77088390 @default.
- W2973454014 hasConcept C90509273 @default.
- W2973454014 hasConceptScore W2973454014C108583219 @default.
- W2973454014 hasConceptScore W2973454014C119857082 @default.
- W2973454014 hasConceptScore W2973454014C154945302 @default.
- W2973454014 hasConceptScore W2973454014C160920958 @default.
- W2973454014 hasConceptScore W2973454014C171268870 @default.
- W2973454014 hasConceptScore W2973454014C199360897 @default.
- W2973454014 hasConceptScore W2973454014C205711294 @default.
- W2973454014 hasConceptScore W2973454014C31972630 @default.
- W2973454014 hasConceptScore W2973454014C34413123 @default.
- W2973454014 hasConceptScore W2973454014C41008148 @default.
- W2973454014 hasConceptScore W2973454014C48044578 @default.
- W2973454014 hasConceptScore W2973454014C50644808 @default.
- W2973454014 hasConceptScore W2973454014C77088390 @default.
- W2973454014 hasConceptScore W2973454014C90509273 @default.
- W2973454014 hasLocation W29734540141 @default.
- W2973454014 hasOpenAccess W2973454014 @default.
- W2973454014 hasPrimaryLocation W29734540141 @default.
- W2973454014 hasRelatedWork W2161047498 @default.
- W2973454014 hasRelatedWork W2296180239 @default.
- W2973454014 hasRelatedWork W2604662268 @default.
- W2973454014 hasRelatedWork W2762815792 @default.
- W2973454014 hasRelatedWork W2766108544 @default.
- W2973454014 hasRelatedWork W2788537278 @default.
- W2973454014 hasRelatedWork W2806669929 @default.
- W2973454014 hasRelatedWork W2902577362 @default.
- W2973454014 hasRelatedWork W2903364556 @default.
- W2973454014 hasRelatedWork W2914433398 @default.
- W2973454014 hasRelatedWork W2931838358 @default.
- W2973454014 hasRelatedWork W2944512428 @default.
- W2973454014 hasRelatedWork W2951738103 @default.
- W2973454014 hasRelatedWork W2955094052 @default.
- W2973454014 hasRelatedWork W2964131627 @default.
- W2973454014 hasRelatedWork W2964290968 @default.
- W2973454014 hasRelatedWork W3052079506 @default.
- W2973454014 hasRelatedWork W3129492404 @default.
- W2973454014 hasRelatedWork W3158779221 @default.
- W2973454014 hasRelatedWork W3206209837 @default.
- W2973454014 isParatext "false" @default.
- W2973454014 isRetracted "false" @default.
- W2973454014 magId "2973454014" @default.
- W2973454014 workType "article" @default.