Vidar：面向通用操作的具身视频扩散模型
Vidar: Embodied Video Diffusion Model for Generalist Manipulation
AI总结：
Vidar通过具身视频扩散模型和掩码逆动力学模型，实现了在不同机器人形态上的通用操作，仅需少量人类演示即可超越现有基线。
摘要：
将通用操作扩展到新的机器人形态仍面临挑战：每个平台通常需要大量的同质演示，而端到端的像素到动作管道在背景和视角变化下可能会退化。基于视频机器人控制的先前进展，我们提出了Vidar，它由一个可推广的先验具身视频扩散模型和一个掩码逆动力学模型（MIDM）作为适配器组成。我们利用在互联网规模上预训练的视频扩散模型，并进一步使用从三个真实机器人平台收集的75万个多视角轨迹对其进行持续预训练。对于这种具身预训练，我们引入了一个统一的观察空间，共同编码机器人、摄像头、任务和场景上下文。MIDM模块在没有密集标签的情况下学习与动作相关的像素掩码，将先验信息接地到目标形态的动作空间，同时抑制干扰项。仅用20分钟的人类演示在未见过的机器人上（仅为典型数据的1%），Vidar在性能上优于最先进的基线，并能泛化到未见过的任务、背景和摄像头布局。我们的结果表明了一种可扩展的“一个先验，多种形态”的配方：强大的、低成本的视频先验与最小的机器人对齐。
英文摘要：
Scaling general-purpose manipulation to new robot embodiments remains challenging: each platform typically needs large, homogeneous demonstrations, and end-to-end pixel-to-action pipelines may degenerate under background and viewpoint shifts. Based on previous advances in video-based robot control, we present Vidar, consisting of an embodied video diffusion model as the generalizable prior and a masked inverse dynamics model (MIDM) as the adapter. We leverage a video diffusion model pre-trained at Internet scale, and further continuously pre-train it for the embodied domain using 750K multi-view trajectories collected from three real-world robot platforms. For this embodied pre-training, we introduce a unified observation space that jointly encodes robot, camera, task, and scene contexts. The MIDM module learns action-relevant pixel masks without dense labels, grounding the prior into the target embodiment's action space while suppressing distractors. With only 20 minutes of human demonstrations on an unseen robot (1% of typical data), Vidar outperforms state-of-the-art baselines and generalizes to unseen tasks, backgrounds, and camera layouts. Our results suggest a scalable recipe for "one prior, many embodiments": strong, inexpensive video priors together with minimal on-robot alignment.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
