Pupavision:把云端大模型装进单板机的果蝇实验监测装置
Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions
科学家用一块 45-75 美元的单板机加摄像头,让 coding agent 常驻设备上自动盯果蝇化蛹实验,断电断网还会推手机提醒。关键是关键采集不依赖 agent,走的确定性代码。做实验室自动化或 DIY 智能硬件的可以看这套分层设计。
Pupavision 是一台成本约 45 到 75 美元的物理 AI 实验仪器,由单板 Linux 计算机和日夜两用摄像头组成,用于自动监测果蝇 Drosophila melanogaster 的化蛹时间。其核心设计是让 frontier coding agent 直接在tiny board 上运行 agentic harness:模型在云端推理,agent 在设备端工作,负责协助图像采集、编写代码修复错误、每天巡检实验以保证原始数据可靠,采集中断时向研究者手机发通知。
可靠性由分层架构保证:一个确定性的采集服务每 10 分钟拍一张图像,完全不依赖 agent。团队报告了 26 天的试点部署(约 3,580 帧),其中包括 agent 登出状态下采集仍持续运行的 11 天,以及一次 51 小时的中断事故——这次故障直接促成了分层设计。分析端采用 researcher-in-the-loop 工作流,从后期参考帧反向追踪选定的蛹,生成每管的化蛹曲线。
论文将其定位为 DIY agentic 仪器的一个早期案例:在确定性代码之上叠加前沿智能,让领域科学家自己搭建实验硬件。后续工作将对照专家标注数据验证化蛹追踪准确性,并扩展实时计算机视觉分析。
Big Brains, Tiny Board: Pupavision, an Agentic Physical AI Instrument for Monitoring Drosophila Pupariation and Lifecycle Transitions
Many biology experiments are limited by the availability and ease of use of instruments that monitor and record them. For example, the timing of pupariation in the fruit fly Drosophila melanogaster, a widely used model organism, can provide biologically relevant information about growth regulation and is often recorded manually. Here, we present Pupavision, a small physical AI instrument built from a single-board Linux computer and a day/night camera for roughly 45 to 75 US dollars in parts. The key idea is that a frontier coding agent runs its agentic harness directly on the tiny board. The model thinks in the cloud, but the agent works on the device. The agent assists image capture, writes code to repair errors, and checks the experiment every day to keep raw data capture reliable. If recording stops, the researcher gets a ping on their mobile phone. A simple deterministic capture service records one image every ten minutes and never depends on the agent. We report a 26-day pilot in a fly incubator (about 3,580 frames), including eleven days in which the agent was logged out and capture continued, and a 51-hour outage whose cause led to the layered design. A researcher-in-the-loop workflow then produces per-vial pupariation curves by tracing selected pupae backward in time from a late reference frame. Future work will validate the assay for lifecycle tracking accuracy against expert-labeled data and expand real-time computer vision analysis. Pupavision offers a blueprint for do-it-yourself agentic instruments that put frontier intelligence on a tiny board, with deterministic code underneath. We present this as an early case study from a pilot lab deployment and contribute lessons learned toward a future where scientific domain experts are empowered by DIY agentic hardware.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:Pupavision、智能体、物理AI、实验室自动化,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Joel Sadler, Daniel Graham, Melanie Worley),经 AITOP 多维评分管线结构化提炼。