Primitive-contrastive network: data-efficient self-supervised learning from robot demonstration videos
Sign Up to like & getrecommendations! Published in 2021 at "Applied Intelligence"
DOI: 10.1007/s10489-021-02527-8
Abstract: Due to the costly collection of expert demonstrations for robots, robot imitation learning suffers from the demonstration-insufficiency problem. A promising solution to this problem is self-supervised learning that leverages pretext tasks to extract general and… read more here.
Keywords: primitive contrastive; self supervised; supervised learning; contrastive network ... See more keywords