実動画からの近似状態推定による物体操作スキルの学習
Learning Object Manipulation Skills via Approximate State Estimation from Real Videos
2D視覚認識と微分可能レンダリングを用いて動画から手と物体の粗い3D状態を教師なしで推定し、その軌道を強化学習の報酬として物体操作スキルを学習、実機ロボットへ転移できることを示した。
著者: Vladimír Petrík, Makarand Tapaswi, Ivan Laptev, Josef Sivic
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to obtain. In this paper, we explore a method that facilitates learning object manipulation skills directly from videos. Leveraging recent advances in 2D visual recognition and differentiable rendering, we develop an optimization based method to estimate a coarse 3D state representation for the hand and the manipulated object(s) without requiring any supervision. We use these trajectories as dense rewards for an agent that learns to mimic them through reinforcement learning. We evaluate our method on simple single- and two-object actions from the Something-Something dataset. Our approach allows an agent to learn actions from single videos, while watching multiple demonstrations makes the policy more robust. We show that policies learned in a simulated environment can be easily transferred to a real robot.
