GenAug

We show that GenAug policies can achieve widespread real-world generalization for tabletop manipulation, even when they are only provided with a few demonstrations in a simple training environment. GenAug: Generative Augmentation for Real-World Data Collection Given the observation of the demonstration environment, GenAug automatically generates “augmented” RGBD images for entirely different and r

[misshiki]

“GenAug（Generative Augmentation）ポリシーは、単純なトレーニング環境でいくつかのデモしか提供されていない場合でも、卓上操作の広範な現実世界の一般化を達成できることを示しています 。”