Matches in SemOpenAlex for { <https://semopenalex.org/work/W4299683911> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4299683911 abstract "Current learning-based robot grasping approaches exploit human-labeled datasets for training the models. However, there are two problems with such a methodology: (a) since each object can be grasped in multiple ways, manually labeling grasp locations is not a trivial task; (b) human labeling is biased by semantics. While there have been attempts to train robots using trial-and-error experiments, the amount of data used in such experiments remains substantially low and hence makes the learner prone to over-fitting. In this paper, we take the leap of increasing the available training data to 40 times more than prior work, leading to a dataset size of 50K data points collected over 700 hours of robot grasping attempts. This allows us to train a Convolutional Neural Network (CNN) for the task of predicting grasp locations without severe overfitting. In our formulation, we recast the regression problem to an 18-way binary classification over image patches. We also present a multi-stage learning approach where a CNN trained in one stage is used to collect hard negatives in subsequent stages. Our experiments clearly show the benefit of using large-scale datasets (and multi-stage training) for the task of grasping. We also compare to several baselines and show state-of-the-art performance on generalization to unseen objects for grasping." @default.
- W4299683911 created "2022-10-02" @default.
- W4299683911 creator A5053034244 @default.
- W4299683911 creator A5056646668 @default.
- W4299683911 date "2015-09-22" @default.
- W4299683911 modified "2023-09-30" @default.
- W4299683911 title "Supersizing Self-supervision: Learning to Grasp from 50K Tries and 700 Robot Hours" @default.
- W4299683911 doi "https://doi.org/10.48550/arxiv.1509.06825" @default.
- W4299683911 hasPublicationYear "2015" @default.
- W4299683911 type Work @default.
- W4299683911 citedByCount "0" @default.
- W4299683911 crossrefType "posted-content" @default.
- W4299683911 hasAuthorship W4299683911A5053034244 @default.
- W4299683911 hasAuthorship W4299683911A5056646668 @default.
- W4299683911 hasBestOaLocation W42996839111 @default.
- W4299683911 hasConcept C119857082 @default.
- W4299683911 hasConcept C12267149 @default.
- W4299683911 hasConcept C127413603 @default.
- W4299683911 hasConcept C134306372 @default.
- W4299683911 hasConcept C154945302 @default.
- W4299683911 hasConcept C165696696 @default.
- W4299683911 hasConcept C171268870 @default.
- W4299683911 hasConcept C177148314 @default.
- W4299683911 hasConcept C199360897 @default.
- W4299683911 hasConcept C201995342 @default.
- W4299683911 hasConcept C22019652 @default.
- W4299683911 hasConcept C2780451532 @default.
- W4299683911 hasConcept C2781238097 @default.
- W4299683911 hasConcept C33923547 @default.
- W4299683911 hasConcept C38652104 @default.
- W4299683911 hasConcept C41008148 @default.
- W4299683911 hasConcept C50644808 @default.
- W4299683911 hasConcept C66905080 @default.
- W4299683911 hasConcept C81363708 @default.
- W4299683911 hasConcept C90509273 @default.
- W4299683911 hasConceptScore W4299683911C119857082 @default.
- W4299683911 hasConceptScore W4299683911C12267149 @default.
- W4299683911 hasConceptScore W4299683911C127413603 @default.
- W4299683911 hasConceptScore W4299683911C134306372 @default.
- W4299683911 hasConceptScore W4299683911C154945302 @default.
- W4299683911 hasConceptScore W4299683911C165696696 @default.
- W4299683911 hasConceptScore W4299683911C171268870 @default.
- W4299683911 hasConceptScore W4299683911C177148314 @default.
- W4299683911 hasConceptScore W4299683911C199360897 @default.
- W4299683911 hasConceptScore W4299683911C201995342 @default.
- W4299683911 hasConceptScore W4299683911C22019652 @default.
- W4299683911 hasConceptScore W4299683911C2780451532 @default.
- W4299683911 hasConceptScore W4299683911C2781238097 @default.
- W4299683911 hasConceptScore W4299683911C33923547 @default.
- W4299683911 hasConceptScore W4299683911C38652104 @default.
- W4299683911 hasConceptScore W4299683911C41008148 @default.
- W4299683911 hasConceptScore W4299683911C50644808 @default.
- W4299683911 hasConceptScore W4299683911C66905080 @default.
- W4299683911 hasConceptScore W4299683911C81363708 @default.
- W4299683911 hasConceptScore W4299683911C90509273 @default.
- W4299683911 hasLocation W42996839111 @default.
- W4299683911 hasLocation W42996839112 @default.
- W4299683911 hasOpenAccess W4299683911 @default.
- W4299683911 hasPrimaryLocation W42996839111 @default.
- W4299683911 hasRelatedWork W1636820063 @default.
- W4299683911 hasRelatedWork W2050305425 @default.
- W4299683911 hasRelatedWork W2068051639 @default.
- W4299683911 hasRelatedWork W2557924869 @default.
- W4299683911 hasRelatedWork W2767651786 @default.
- W4299683911 hasRelatedWork W2889260105 @default.
- W4299683911 hasRelatedWork W2989932438 @default.
- W4299683911 hasRelatedWork W3081496756 @default.
- W4299683911 hasRelatedWork W3099765033 @default.
- W4299683911 hasRelatedWork W4321376912 @default.
- W4299683911 isParatext "false" @default.
- W4299683911 isRetracted "false" @default.
- W4299683911 workType "article" @default.