# Curie's Jarvis系统实现无标记桌面化学实验自主操作

> 原文链接：https://robotics.hellobike.com/papers/2026-11-11-2611-13251-23fdec7c
> 频道：papers | 更新日期：2026-11-11 | 标签：auto, arxiv
> 核心摘要：Curie's Jarvis系统使机械臂能在人类实验台自主执行化学实验，无需固定夹具或基准标记。基于Franka Panda平台，该系统通过视觉识别打印协议与容器标签，在儿童化学试剂盒测试中实现5/5与4/5成功率，160次标签识别零误差。

# Curie's Jarvis系统实现无标记桌面化学实验自主操作

::: v-pre
> 本文由 AI 根据公开内容整理，可能有误，请以原文为准：[Curie's Jarvis: Autonomous Robotic Chemistry Experiments from Printed Protocols](https://arxiv.org/abs/2611.13251)（arXiv 2611.13251）

## 核心内容

针对传统实验室自动化依赖脚本与固定工装的局限，研究团队推出Curie's Jarvis系统，使机器人能像人类一样依据打印指令在非结构化桌面执行化学实验。该系统搭载于Franka Panda机械臂，在无人干预下完成儿童化学试剂盒测试，两个协议分别取得5/5和4/5的成功率，并在160次打印及手写标签定位任务中实现100%识别准确率，验证了非结构化环境下的操作鲁棒性。

技术上，系统通过相机读取打印实验步骤照片解析流程，利用四视角视觉融合识别无标记容器标签以区分外观相同器皿。每步操作前重新定位目标，并根据被操作对象属性动态调整抓取速度等参数。该架构摆脱了对基准标记（fiducial markers）和固定位置的依赖，实现了从“机器专用”向“人机共用”实验环境的范式迁移，显著降低了实验室自动化部署门槛。

## 关键看点

- **非结构化适配**：支持人类标准实验台，无需固定位置或基准标记，通过四视角视觉融合识别容器标签并动态重定位目标
- **协议解析能力**：直接读取打印版实验步骤照片生成执行逻辑，根据被操作对象属性自适应调整动作速度等参数
- **实测验证数据**：Franka Panda平台无人干预下完成两组儿童化学实验，成功率分别为100%与80%，160次标签识别零误判

## 工程与产业观察

该工作验证了具身智能在非结构化科研场景的落地潜力，通过视觉语义理解替代精密工装，解决了实验室自动化长尾需求。其“读图即执行”与动态重定位机制，为通用操作机器人在柔性制造、生物制药等非标环境的应用提供了可复用的感知-规划技术范式。

## 英文摘要 (Abstract)

A person running a bench experiment works from a printed instruction sheet, tells identical containers apart by the labels written on them, and looks at the bench again before each step. Lab automation usually works the other way around: the procedure is written as a script, and containers stand at fixed positions or carry fiducial markers. We present Curie's Jarvis, a system that lets a robot arm carry out a chemistry experiment on a bench set up for people. It reads the steps from a photo of the printed sheet, finds containers on an ordinary bench with no fixed positions or markers, tells identical-looking containers apart by reading their labels in four camera views, locates its target again before every step, and sets how each step is carried out, including its speed, from what is being handled. On a Franka Panda arm, Curie's Jarvis completed 5 of 5 runs of one protocol from a children's chemistry kit and 4 of 5 runs of another, with no human intervention, and in 160 locates on printed and handwritten labels it identified every container correctly. This brings robots a step closer to doing bench chemistry the way people do.

作者：Rumi Loghmani, Bozhang Song, Victor Alvarado, Aliyah Redding, Amir Barati Farimani
:::

## 原始参考来源 (Sources)

- [arXiv 2611.13251：Curie's Jarvis: Autonomous Robotic Chemistry Experiments from Printed Protocols](https://arxiv.org/abs/2611.13251)