RoboTrustBench：机器人操作视频世界模型的可信度基准测试
RoboTrustBench: Benchmarking the Trustworthiness of Video World Models for Robotic Manipulation
AI总结：
针对视频世界模型在机器人操作中的可信度问题，提出RoboTrustBench基准，包含正常、约束敏感、反事实和对抗四种场景，通过专家验证的指令-图像对和六维评估协议，发现当前模型在约束推理、反事实基础、物理交互和不安全指令抑制方面存在不足。
摘要：
视频世界模型越来越多地用于机器人操作，然而现有基准大多在有效、可行和安全的指令下评估它们。我们引入了RoboTrustBench，一个用于评估视频世界模型在四种场景下可信度的基准：正常、约束敏感、反事实和对抗。基于真实世界的DROID片段构建，RoboTrustBench包含1,207个专家验证的指令-图像对和一个六维评估协议，包含13个细粒度标准。通过人类和MLLM评估七个代表性的视频世界模型，我们发现当前模型通常生成视觉上连贯的视频，但在约束推理、反事实基础、物理交互和不安全指令抑制方面存在困难。这些结果表明，视觉质量和表面级别的指令遵循不足以实现可信赖的机器人视频世界建模。
英文摘要：
Video world models are increasingly used in robotic manipulation, yet existing benchmarks mostly evaluate them under valid, feasible, and safe instructions. We introduce RoboTrustBench, a benchmark for evaluating the trustworthiness of video world models under four scenarios: Normal, Constraint-Sensitive, Counterfactual, and Adversarial. Built from real-world DROID episodes, RoboTrustBench contains 1,207 expert-validated instruction-image pairs and a six-dimensional evaluation protocol with 13 fine-grained criteria. Evaluating seven representative video world models with human and MLLM assessment, we find that current models often generate visually coherent videos, but struggle with constraint reasoning, counterfactual grounding, physical interaction, and unsafe-instruction suppression. These results show that visual quality and surface-level instruction following are insufficient for trustworthy robotic video world modeling.
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。
