arXiv cs.AI· Lorenzo Mazza, Ariel Rodriguez, Stefanie Speidel·· 1 天前AI 评分24
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
AI 导读
Sensorium 是一个基于 ROS/ROS2 的开源 Python 库，用于从可配置的机器人与传感器流中录制、处理、标注和整理多模态手术数据，并生成片段式数据集。研究团队在 1516 次体模、离体与活体猪实验中对其进行了评估，覆盖多种手术任务与传感配置，并报告了初步的可用性反馈。
正文 · 原文
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.
| Comments: | GenAI for Health Workshop @ NeurIPS 2026, Sydney |
| Subjects: | Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.41946 [cs.AI] |
| (or arXiv:2610.41946v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.41946 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ariel Rodriguez [view email]
[v1]
Fri, 30 Oct 2026 16:04:23 UTC (14,409 KB)
来源：arXiv cs.AI · arxiv.org