Sensorium：面向具身手术 AI 的开源多模态数据采集与整理库
Sensorium: An Open-Source Multimodal Data Collection and Curation Library for Embodied Surgical AI
Lorenzo Mazza · Ariel Rodriguez · Stefanie Speidel
中文摘要
具身手术 AI 需要可靠的多模态（multimodal）数据，但手术数据采集成本高、难以重复，且高度依赖硬件配置。Sensorium 是一个开源 Python 库，基于机器人操作系统（ROS）与 ROS2 中间件，从可配置的机器人与传感器数据流中完成多模态手术数据的记录、处理、标注与整理。该库整合了面向操作者的数据采集、可配置处理、语义标注与片段化数据集生成。在涉及多种手术任务与传感配置的 1516 次体模、离体与活体猪实验记录上对 Sensorium 进行了评估，并报告了初步的可用性反馈。
关键要点
- 01手术数据采集成本高、难复现且依赖硬件，缺乏统一工具
- 02基于 ROS/ROS2 的开源 Python 库，覆盖采集、处理、标注与数据集生成
- 03在 1516 次体模、离体与活体猪实验中验证，覆盖多任务与多传感配置
- 04仅报告初步可用性反馈，尚未给出下游模型性能评估
解读
尚无解读。
原始英文摘要
arXiv:2610.41946v1 Announce Type: cross Abstract: Embodied surgical AI requires reliable multimodal data, yet surgical data collection remains costly, difficult to repeat, and strongly dependent on the hardware setup. We present Sensorium, an open-source Python library for recording, processing, annotating, and curating multimodal surgical data from configurable robot and sensor streams using the Robot Operating System (ROS) and ROS2 middleware. The library combines operator-facing data acquisition, configurable processing, semantic annotation, and episodic dataset generation. We evaluate Sensorium across 1516 recordings of phantom, ex vivo, and in vivo porcine experiments involving multiple surgical tasks and sensing configurations, and report preliminary usability feedback.