異種マスク付き自己回帰による実世界の行動-映像ダイナミクスの学習
Learning Real-World Action-Video Dynamics with Heterogeneous Masked Autoregression
異なるロボットの身体・環境・タスクの観察と行動列を統合的に事前学習し、マスク付き自己回帰で映像を予測するモデルHMAを提案。従来のロボット映像生成より高品質かつ15倍高速で、ポリシー評価や合成データ生成に使える映像シミュレータとして機能する。
著者: Lirui Wang, Kevin Zhao, Chaoqi Liu, Xinlei Chen
分類: cs.RO, cs.CV, cs.LG
原文アブストラクト
We propose Heterogeneous Masked Autoregression (HMA) for modeling action-video dynamics to generate high-quality data and evaluation in scaling robot learning. Building interactive video world models and policies for robotics is difficult due to the challenge of handling diverse settings while maintaining computational efficiency to run in real time. HMA uses heterogeneous pre-training from observations and action sequences across different robotic embodiments, domains, and tasks. HMA uses masked autoregression to generate quantized or soft tokens for video predictions. \ourshort achieves better visual fidelity and controllability than the previous robotic video generation models with 15 times faster speed in the real world. After post-training, this model can be used as a video simulator from low-level action inputs for evaluating policies and generating synthetic data. See this link https://liruiw.github.io/hma for more information.
