自己教師あり対応学習による視覚運動ポリシーの汎化
Self-Supervised Correspondence in Visuomotor Policy Learning
密な視覚対応を自己教師ありで学習し、それを視覚運動ポリシーの訓練に用いることで、少ないデモ数でも物体クラスや変形物体、無テクスチャ物体に汎化する模倣学習ポリシーを実現した。
著者: Peter Florence, Lucas Manuelli, Russ Tedrake
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
In this paper we explore using self-supervised correspondence for improving the generalization performance and sample efficiency of visuomotor policy learning. Prior work has primarily used approaches such as autoencoding, pose-based losses, and end-to-end policy optimization in order to train the visual portion of visuomotor policies. We instead propose an approach using self-supervised dense visual correspondence training, and show this enables visuomotor policy learning with surprisingly high generalization performance with modest amounts of data: using imitation learning, we demonstrate extensive hardware validation on challenging manipulation tasks with as few as 50 demonstrations. Our learned policies can generalize across classes of objects, react to deformable object configurations, and manipulate textureless symmetrical objects in a variety of backgrounds, all with closed-loop, real-time vision-based policies. Simulated imitation learning experiments suggest that correspondence training offers sample complexity and generalization benefits compared to autoencoding and end-to-end training.
