A visual encoder pre-trained on diverse human videos with contrastive and language objectives improves simulated robot manipulation success by over 20% versus training from scratch and enables real Franka arm tasks from 20 demonstrations.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2022 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
R3M: A Universal Visual Representation for Robot Manipulation
A visual encoder pre-trained on diverse human videos with contrastive and language objectives improves simulated robot manipulation success by over 20% versus training from scratch and enables real Franka arm tasks from 20 demonstrations.