Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292669268> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4292669268 abstract "Deep learning-based robotic grasping has made significant progress thanks to algorithmic improvements and increased data availability. However, state-of-the-art models are often trained on as few as hundreds or thousands of unique object instances, and as a result generalization can be a challenge. In this work, we explore a novel data generation pipeline for training a deep neural network to perform grasp planning that applies the idea of domain randomization to object synthesis. We generate millions of unique, unrealistic procedurally generated objects, and train a deep neural network to perform grasp planning on these objects. Since the distribution of successful grasps for a given object can be highly multimodal, we propose an autoregressive grasp planning model that maps sensor inputs of a scene to a probability distribution over possible grasps. This model allows us to sample grasps efficiently at test time (or avoid sampling entirely). We evaluate our model architecture and data generation pipeline in simulation and the real world. We find we can achieve a $>$90% success rate on previously unseen realistic objects at test time in simulation despite having only been trained on random objects. We also demonstrate an 80% success rate on real-world grasp attempts despite having only been trained on random simulated objects." @default.
- W4292669268 created "2022-08-23" @default.
- W4292669268 creator A5003685124 @default.
- W4292669268 creator A5009926169 @default.
- W4292669268 creator A5010674841 @default.
- W4292669268 creator A5026829243 @default.
- W4292669268 creator A5036908757 @default.
- W4292669268 creator A5041107386 @default.
- W4292669268 creator A5049349154 @default.
- W4292669268 creator A5055942061 @default.
- W4292669268 creator A5061323862 @default.
- W4292669268 creator A5076651586 @default.
- W4292669268 creator A5091819924 @default.
- W4292669268 date "2017-10-17" @default.
- W4292669268 modified "2023-09-23" @default.
- W4292669268 title "Domain Randomization and Generative Models for Robotic Grasping" @default.
- W4292669268 doi "https://doi.org/10.48550/arxiv.1710.06425" @default.
- W4292669268 hasPublicationYear "2017" @default.
- W4292669268 type Work @default.
- W4292669268 citedByCount "0" @default.
- W4292669268 crossrefType "posted-content" @default.
- W4292669268 hasAuthorship W4292669268A5003685124 @default.
- W4292669268 hasAuthorship W4292669268A5009926169 @default.
- W4292669268 hasAuthorship W4292669268A5010674841 @default.
- W4292669268 hasAuthorship W4292669268A5026829243 @default.
- W4292669268 hasAuthorship W4292669268A5036908757 @default.
- W4292669268 hasAuthorship W4292669268A5041107386 @default.
- W4292669268 hasAuthorship W4292669268A5049349154 @default.
- W4292669268 hasAuthorship W4292669268A5055942061 @default.
- W4292669268 hasAuthorship W4292669268A5061323862 @default.
- W4292669268 hasAuthorship W4292669268A5076651586 @default.
- W4292669268 hasAuthorship W4292669268A5091819924 @default.
- W4292669268 hasBestOaLocation W42926692681 @default.
- W4292669268 hasConcept C107673813 @default.
- W4292669268 hasConcept C108583219 @default.
- W4292669268 hasConcept C119857082 @default.
- W4292669268 hasConcept C134306372 @default.
- W4292669268 hasConcept C154945302 @default.
- W4292669268 hasConcept C167966045 @default.
- W4292669268 hasConcept C171268870 @default.
- W4292669268 hasConcept C177148314 @default.
- W4292669268 hasConcept C177769412 @default.
- W4292669268 hasConcept C199360897 @default.
- W4292669268 hasConcept C2781238097 @default.
- W4292669268 hasConcept C33923547 @default.
- W4292669268 hasConcept C36503486 @default.
- W4292669268 hasConcept C39890363 @default.
- W4292669268 hasConcept C41008148 @default.
- W4292669268 hasConcept C43521106 @default.
- W4292669268 hasConceptScore W4292669268C107673813 @default.
- W4292669268 hasConceptScore W4292669268C108583219 @default.
- W4292669268 hasConceptScore W4292669268C119857082 @default.
- W4292669268 hasConceptScore W4292669268C134306372 @default.
- W4292669268 hasConceptScore W4292669268C154945302 @default.
- W4292669268 hasConceptScore W4292669268C167966045 @default.
- W4292669268 hasConceptScore W4292669268C171268870 @default.
- W4292669268 hasConceptScore W4292669268C177148314 @default.
- W4292669268 hasConceptScore W4292669268C177769412 @default.
- W4292669268 hasConceptScore W4292669268C199360897 @default.
- W4292669268 hasConceptScore W4292669268C2781238097 @default.
- W4292669268 hasConceptScore W4292669268C33923547 @default.
- W4292669268 hasConceptScore W4292669268C36503486 @default.
- W4292669268 hasConceptScore W4292669268C39890363 @default.
- W4292669268 hasConceptScore W4292669268C41008148 @default.
- W4292669268 hasConceptScore W4292669268C43521106 @default.
- W4292669268 hasLocation W42926692681 @default.
- W4292669268 hasOpenAccess W4292669268 @default.
- W4292669268 hasPrimaryLocation W42926692681 @default.
- W4292669268 hasRelatedWork W2557924869 @default.
- W4292669268 hasRelatedWork W2786068615 @default.
- W4292669268 hasRelatedWork W2888481972 @default.
- W4292669268 hasRelatedWork W2918377940 @default.
- W4292669268 hasRelatedWork W2945136467 @default.
- W4292669268 hasRelatedWork W2963326767 @default.
- W4292669268 hasRelatedWork W3004284873 @default.
- W4292669268 hasRelatedWork W3034263774 @default.
- W4292669268 hasRelatedWork W4223943233 @default.
- W4292669268 hasRelatedWork W4226073023 @default.
- W4292669268 isParatext "false" @default.
- W4292669268 isRetracted "false" @default.
- W4292669268 workType "article" @default.