发表机构
Karlsruhe Institute of Technology; Hunan University（卡尔斯鲁厄理工学院; 湖南大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
INSPECT通过智能眼镜助手记录学习机器人视角选择，利用PI-TwinSwap校准和声明索引监督，提升装配检查的视角效用和可验证性。
AI 中文摘要
检查装配体的机器人必须确定哪些零件存在以及它们是否正确安装。在自我中心的装配辅助过程中，头部运动和工件操作揭示了这些检查的证据，而口头状态确认将观察结果与程序结果联系起来。我们引入了INSPECT，它从智能眼镜助手的记录中学习机器人的视角偏好，该助手回答零件查询并提供下一步指导。存在不变孪生交换（PI-TwinSwap）通过成对的身份干预来校准对象证据。声明索引的监督将证据要求与相机可重现的观察变化分开。以对象为中心的校准将相对视角偏好适应机器人姿态，而子句级筛选检查预测的证据。机器人仅使用其当前观察和已知姿态选择视角，无需候选图像。评估使用带注释的助手视频重放来模拟状态反馈，无需目标域视角标签用于策略训练。在物理齿轮箱装配体的图像上，INSPECT在比较的非神谕策略中实现了最高的视角效用，并将人类评级的完全可验证性从34.8%提高到41.7%，相比保持当前视角。在IMPACT中的商用角磨机录音上，转移的相对视角选择器将正确决策率从50.6%提高到54.3%，使用冻结的感知头。源代码可在该https URL获取。
英文摘要
Robots inspecting an assembly must determine which parts are present and whether they are correctly installed. During egocentric assembly assistance, head motion and workpiece handling reveal evidence for these checks, while spoken state confirmations link observations to procedural outcomes. We introduce INSPECT, which learns robot view preferences from records of a smart-glasses assistant that answers part queries and provides next-step guidance. Presence-Invariant TwinSwap (PI-TwinSwap) calibrates object evidence through paired identity interventions. Claim-indexed supervision separates evidence requirements from camera-reproducible observation changes. Object-centered calibration adapts relative view preferences to robot poses, while clause-level screening checks predicted evidence. The robot selects views using only its current observation and known poses, without candidate images. Evaluation uses annotated assistant-video replay to simulate state feedback, without target-domain view labels for policy training. On images of physical gearbox assemblies, INSPECT achieves the highest view utility among the compared non-oracle policies and raises human-rated full verifiability from 34.8% to 41.7% compared with keeping the current view. On commercial angle-grinder recordings in IMPACT, the transferred relative-view selector increases the correct decision rate from 50.6% to 54.3% with a frozen perception head. The source code is available at https://github.com/Kratos-Wen/INSPECT.
Comments9 pages, 3 figures, 5 tables. Code: https://github.com/Kratos-Wen/INSPECT
