An architecture that pairs two learned models generates ranked dexterous grasps from a single depth view, reaching 87.8% real-robot success on novel objects versus a 57.1% generative-only baseline.
Data-driven grasp synthesis – a survey,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Deep Dexterous Grasping of Novel Objects from a Single View
An architecture that pairs two learned models generates ranked dexterous grasps from a single depth view, reaching 87.8% real-robot success on novel objects versus a 57.1% generative-only baseline.