paper-with-me

CALVIN

Composing Actions from Language and Vision

홈페이지 · 논문 65편

CALVIN (Composing Actions from Language and Vision), is an open-source simulated benchmark to learn long-horizon language-conditioned robot manipulation tasks.

벤치마크

Robot Manipulation on CALVIN 결과 23개
Zero-shot Generalization on CALVIN 결과 5개