X-Diffusion：在跨具身人类示范上训练扩散策略
X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
AI总结：
本文提出X-Diffusion框架，通过在噪声人类动作上训练扩散策略，提升机器人任务成功率16%。
摘要：
人类视频是机器人学习的可扩展数据源。然而，人类与机器人在具身上存在显著差异，使许多人类动作无法直接在机器人上执行。但这些示范传达了丰富的物体交互线索和任务意图。我们的目标是学习这种粗略指导，而不转移具身特定、不可行的执行策略。最近的生成建模进展解决了从低质量数据学习的问题。特别是，Ambient Diffusion是一种扩散建模方法，仅在正向扩散过程的高噪声时间步整合低质量数据。我们的关键见解是将人类动作视为机器人动作的噪声版本。随着噪声增加，具身差异减弱，而任务相关指导保持不变。基于这些观察，我们提出了X-Diffusion，一种基于Ambient Diffusion的跨具身学习框架，选择性地在噪声人类动作上训练扩散策略。这使机器人能够有效利用易于收集的人类视频，而不牺牲可行性。在五个现实世界操作任务中，X-Diffusion在naive co-training和手动数据过滤上平均成功率提高了16%。项目网站可在https://portal-cornell.github.io/X-Diffusion/上找到。
英文摘要：
Human videos are a scalable source of training data for robot learning. However, humans and robots significantly differ in embodiment, making many human actions infeasible for direct execution on a robot. Still, these demonstrations convey rich object-interaction cues and task intent. Our goal is to learn from this coarse guidance without transferring embodiment-specific, infeasible execution strategies. Recent advances in generative modeling tackle a related problem of learning from low-quality data. In particular, Ambient Diffusion is a recent method for diffusion modeling that incorporates low-quality data only at high-noise timesteps of the forward diffusion process. Our key insight is to view human actions as noisy counterparts of robot actions. As noise increases along the forward diffusion process, embodiment-specific differences fade away while task-relevant guidance is preserved. Based on these observations, we present X-Diffusion, a cross-embodiment learning framework based on Ambient Diffusion that selectively trains diffusion policies on noised human actions. This enables effective use of easy-to-collect human videos without sacrificing robot feasibility. Across five real-world manipulation tasks, we show that X-Diffusion improves average success rates by 16% over naive co-training and manual data filtering. The project website is available at https://portal-cornell.github.io/X-Diffusion/.
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。
