R3m: A universal visual representation for robot manipulation

S Nair, A Rajeswaran, V Kumar, C Finn… - arXiv preprint arXiv …, 2022 - arxiv.org
We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …
被引用次数：353 相关文章

R3M: A Universal Visual Representation for Robot Manipulation

S Nair, A Rajeswaran, V Kumar, C Finn… - 6th Annual Conference on … - openreview.net
We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …

R3M: A Universal Visual Representation for Robot Manipulation

S Nair, A Rajeswaran, V Kumar, C Finn… - arXiv e …, 2022 - ui.adsabs.harvard.edu
We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …

R3M: A Universal Visual Representation for Robot Manipulation

S Nair, A Rajeswaran, V Kumar… - Conference on Robot …, 2023 - proceedings.mlr.press
We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …
[PDF] researchgate.net

[PDF][PDF] R3M: A Universal Visual Representation for Robot Manipulation

S Nair, A Rajeswaran, V Kumar, C Finn… - arXiv preprint arXiv …, 2022 - researchgate.net
We study how visual representations pre-trained on diverse human video data can enable
data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a …