Sensorium: An Open-Source Multimodal Data Collection and Curation Library for Embodied Surgical AI
Sensorium: An Open-Source Multimodal Data Collection and Curation Library for Embodied Surgical AI
This paper introduces Sensorium, an open-source Python library designed to record, process, annotate, and curate multimodal surgical data from configurable robot and sensor streams using ROS and ROS2. The authors evaluate the library across 1516 recordings involving phantom, ex vivo, and in vivo porcine experiments with multiple surgical tasks and sensing configurations, reporting preliminary usability feedback.
The authors present Sensorium, an open-source Python library for collecting and curating multimodal surgical data using ROS/ROS2, evaluated across 1516 recordings of phantom, ex vivo, and in vivo porcine experiments; preliminary usability feedback is reported but independent validation of the library's performance in clinical settings is not provided.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
recordings
1,516
Reported trials
View original evidence
em (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.
Open source S3
Dataset details reported by the source
- Modalities
- multimodal surgical data Open source S2
- Tasks
- multiple surgical tasks Open source S3
- Embodiments
- configurable robot and sensor streams Open source S2
- paper: not_reported
- weights: not_reported
- dataset: not_reported
What remains unknown
Dataset licensing and commercial-use rights are not established here.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
em (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.
Open source S3
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 Syst
Open source S2
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Confirm the required data type and collection setting with the buyer; this source does not establish a complete collection specification.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Check the exact dataset version, license, modalities and task coverage against the intended use.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org