RoboWM-Bench：用于评估机器人操作中世界模型的基准
RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation
AI总结：
本文提出RoboWM-Bench，用于评估视频世界模型在机器人操作中的执行能力，发现视觉合理性与实际执行性不一致，并分析了影响执行性能的因素。
摘要：
近年来，大规模视频世界模型的进步使未来预测更加逼真，为机器人学习提供了可扩展的监督。然而，对于具身操作，感知真实性不足以满足需求：生成的交互必须在物理上一致且能被机器人代理执行。现有基准评估了视觉质量和物理合理性，但未系统评估预测行为是否能转化为可执行动作完成操作任务。我们引入RoboWM-Bench，一个以操作为中心的基准，用于评估视频世界模型的具身化表现。RoboWM-Bench将生成的人手和机器人操作视频转换为具身动作序列，并通过物理基础的模拟环境验证。基于真实到模拟的场景重建和多样的操作任务，RoboWM-Bench实现了标准化、可重复和可扩展的物理可执行性评估。使用RoboWM-Bench，我们评估了最先进的视频世界模型，并发现视觉合理性和具身可执行性并不总是一致。我们的分析指出了一些影响执行性能的反复出现因素，包括空间推理、接触预测和非物理几何失真，特别是在复杂和长周期交互中。这些发现提供了对当前模型能力的更细致视角，并强调了具身意识评估在指导物理基础世界建模中的价值。
英文摘要：
Recent advances in large-scale video world models have enabled increasingly realistic future prediction, raising the prospect of using generated videos as scalable supervision for robot learning. However, for embodied manipulation, perceptual realism alone is not sufficient: generated interactions must also be physically consistent and executable by robotic agents. Existing benchmarks provide valuable assessments of visual quality and physical plausibility, but they do not systematically evaluate whether predicted behaviors can be translated into executable actions that complete manipulation tasks. We introduce RoboWM-Bench, a manipulation-centric benchmark for embodiment-grounded evaluation of video world models. RoboWM-Bench converts generated human-hand and robotic manipulation videos into embodied action sequences and validates them through execution in physically grounded simulation environments. Built on real-to-sim scene reconstruction and diverse manipulation tasks, RoboWM-Bench enables standardized, reproducible, and scalable evaluation of physical executability. Using RoboWM-Bench, we evaluate state-of-the-art video world models and observe that visual plausibility and embodied executability are not always aligned. Our analysis highlights several recurring factors that affect execution performance, including spatial reasoning, contact prediction, and non-physical geometric distortions, particularly in complex and long-horizon interactions. These findings provide a more fine-grained view of current model capabilities and underscore the value of embodiment-aware evaluation for guiding physically grounded world modeling in robotic manipulation.
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。
