{"@context":"https://schema.org","@type":"NewsArticle","generatedAt":"2026-07-23T07:21:26.498Z","headline":"Hugging Face 发布 Grabette：开源手持夹爪系统，无需机器人即可录制操作数据","description":"Hugging Face 推出 Grabette，一套开源低成本系统，用户手持夹爪即可在几分钟内录制操作演示，并自动生成机器人可用的数据集。Grabette 配备鱼眼相机与 RGBD 相机，通过 SLAM 恢复 6-DoF 轨迹，硬件物料成本约 490 欧元。所有硬件设计、处理流程与训练代码均开源，数据以标准 LeRobot 格式上传至 Hugging Face Hub，支持任意机器人后端。","url":"https://www.aioga.com/news/cmruh5yy2040vbi07twmqcnwq/","mainEntityOfPage":"https://www.aioga.com/news/cmruh5yy2040vbi07twmqcnwq/","datePublished":"2026-07-21T00:00:00.000Z","dateModified":"2026-07-21T00:00:00.000Z","inLanguage":"zh-CN","publisher":{"@type":"NewsMediaOrganization","name":"Aioga","url":"https://www.aioga.com"},"citation":["https://huggingface.co/blog/grabette","https://aihot.virxact.com/items/cmruh5yy2040vbi07twmqcnwq"],"canonicalUrl":"https://www.aioga.com/news/cmruh5yy2040vbi07twmqcnwq/","directAnswer":{"@type":"Answer","text":"Aioga 编辑摘要：Hugging Face 推出 Grabette，一套开源低成本系统，用户手持夹爪即可在几分钟内录制操作演示，并自动生成机器人可用的数据集。 Aioga 将其归入「产品更新」方向，重点关注它对真实使用和行业竞争的影响。","url":"https://www.aioga.com/news/cmruh5yy2040vbi07twmqcnwq/","dateCreated":"2026-07-21T00:00:00.000Z","author":{"@type":"Organization","@id":"https://www.aioga.com/authors/aioga-editorial/#editorial-team","name":"Aioga Editorial Team","url":"https://www.aioga.com/authors/aioga-editorial/"}},"evidence":[{"@type":"CreativeWork","name":"huggingface.co source article","url":"https://huggingface.co/blog/grabette","datePublished":"2026-07-21T00:00:00.000Z","provider":{"@type":"Organization","name":"huggingface.co","url":"https://huggingface.co/blog/grabette"}},{"@type":"CreativeWork","name":"AIHot archive record","url":"https://aihot.virxact.com/items/cmruh5yy2040vbi07twmqcnwq","datePublished":"2026-07-21T00:00:00.000Z","provider":{"@type":"Organization","name":"AIHot","url":"https://aihot.virxact.com/items/cmruh5yy2040vbi07twmqcnwq"}}],"aggregationSource":"Hugging Face：Blog（RSS）","originalPublisher":{"name":"huggingface.co","url":"https://huggingface.co/blog/grabette"},"article":{"id":"cmruh5yy2040vbi07twmqcnwq","slug":"cmruh5yy2040vbi07twmqcnwq","url":"https://www.aioga.com/news/cmruh5yy2040vbi07twmqcnwq/","title":"Hugging Face 发布 Grabette：开源手持夹爪系统，无需机器人即可录制操作数据","title_en":"Grabette： an open system to record robot-manipulation data","summary":"Hugging Face 推出 Grabette，一套开源低成本系统，用户手持夹爪即可在几分钟内录制操作演示，并自动生成机器人可用的数据集。Grabette 配备鱼眼相机与 RGBD 相机，通过 SLAM 恢复 6-DoF 轨迹，硬件物料成本约 490 欧元。所有硬件设计、处理流程与训练代码均开源，数据以标准 LeRobot 格式上传至 Hugging Face Hub，支持任意机器人后端。","source":"Hugging Face：Blog（RSS）","sourceUrl":"https://huggingface.co/blog/grabette","aiHotUrl":"https://aihot.virxact.com/items/cmruh5yy2040vbi07twmqcnwq","publishedAt":"2026-07-21T00:00:00.000Z","category":"产品更新","score":53,"selected":false,"articleBody":["The bottleneck isn’t the model. It’s the data. ：#the-bottleneck-isnt-the-model-its-the-data Standing on the shoulders of UMI ：#standing-on-the-shoulders-of-umi Meet Grabette ：#meet-grabette Built for everyone ：#built-for-everyone From your hand to a dataset, in two steps ：#from-your-hand-to-a-dataset-in-two-steps 1. Record ：#1-record 2. Process, directly in your browser ：#2-process-directly-in-your-browser What can you do with the data? Here’s one example. ：#what-can-you-do-with-the-data-heres-one-example Now it's your turn ：#now-its-your-turn What's next ：#whats-next Record your own manipulation tasks in minutes with a handheld gripper, turn them into robot-ready datasets automatically, and help grow an open, collaborative dataset for robot learning.","Robot learning has a supply problem. We have capable policy architectures (transformer-based VLAs, diffusion and flow-matching policies, and even world models) and the GPUs to train them. What we lack is large, diverse, real-world manipulation data.","Teleoperating a robot to collect it can be expensive and demanding: first of all, it requires a robot . And depending on the teleoperation method, data collection can be tedious for the user if it takes hours and involve significant hardware and logistical challenges. That is difficult to scale with the wide variety of tasks and environnements required.","But you don't need a robot to collect robot data. Just a human hand, a gripper, a camera, and a way to recover the 6-DoF trajectory of what the hand did. Capture the demonstration and you have data a robot can learn from.","That's what we're releasing today: Grabette, an open, low-cost system for recording manipulation data. Pick it up, record a task with your own hand, and get back a clean, robot-ready dataset. No robot, no lab, no teleop rig.","And that's the bigger goal: if recording a demonstration is as easy as shooting a video, anyone can contribute. We want Grabette to seed a large, open, collaborative manipulation dataset . One no single lab could ever build alone.","Grabette is directly inspired by the Universal Manipulation Interface (UMI)：https://umi-gripper.github.io/ from Stanford: a handheld gripper with a fisheye camera that records demonstrations \"in the wild\", recovers camera trajectories with SLAM, and trains visuomotor policies from them.","UMI proved the recipe works. Other (closed source) devices exists like Agibot's MEgo gripper, Genrobot's DAS gripper and Sunday Robotics skill capture glove. Our goal was to make it effortless to use, to get the barrier from \"I have a task\" to \"I have a trained model\" as low as possible.","Grabette is built into the modern open ecosystem: LeRobot for datasets, the Hugging Face Hub for sharing, and a processing pipeline you run from your browser with nothing to install. Grabette is something anyone can build on a workbench, use in the field, and contribute data from.","We have been developing Grabette for months, and we feel it has become usable enough to share. We are excited to share it now with you!","Grabette is a handheld gripper instrumented with everything needed to reconstruct a manipulation demonstration.","It carries two cameras, each with a distinct job. Splitting the two roles is deliberate: the cheap wide fisheye gives the policy the context-rich, wrist-camera-style view it needs, while the RGBD camera does the heavy lifting of robust 6-DoF tracking.","And while Grabette records data during tasks performed by a user, it relies on its robotic counterpart to execute the movements it has learned after training. So, meet Gripette , the robotic arm end-effector twin of Grabette.","The family shares the same hardware DNA:","Grabette hand held recording device (left) and Gripette robot gripper (right)","Go check the repository!：https://github.com/pollen-robotics/grabette","Components. Standard sensors you can buy, no closed pipeline, no fork lock-in. A Raspberry Pi, a standard Pi camera, an off-the-shelf OAK-D depth camera, magnetic encoders. The whole point is that anyone can build one from parts you can just order.","Robot-agnostic by design. Nothing in the capture or the data format assumes a particular arm. Demonstrations are stored as camera-local 6-DoF cartesian pose plus gripper state, the output is a standard LeRobot dataset on the Hugging Face Hub, so the same data can drive different robots and different learning methods. You will still need the matching Gripette gripper on your arm though.","This release enables anyone to go from \"I want to demonstrate a task\" to \"I have a training-ready dataset\" quickly and without prior expertise.","Press the button, and data from the observation camera, the tracking camera (color, depth, and IMU), and the gripper’s encoder joint values are recorded simultaneously, using a single shared clock to ensure proper synchronization. Press the button again to stop the episode, and the data is saved locally on the Raspberry Pi.","：https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/grabette/Browser_postprocess_small2.gif","Open the Grabette dashboard in your browser. Select the episodes you want to add to the dataset, and with one click, post-processing begins.","Everything is now ready to start training!","A dataset is only interesting if it trains something. So, to show the loop end-to-end, we ship a complete example. But to be clear, this is an example of what is enables, not the product: the release is the recording system. Your Grabette data works with any method that consumes LeRobot datasets.","Our example takes 200 recorded demonstrations such as :","Dataset available on this HF Dataset：https://huggingface.co/datasets/chouziel/dataset-cup-0107","Policy available on this HF Model：https://huggingface.co/SteveNguyen/pick_cup_0107_smooth-best","The data bottleneck doesn’t get solved by one lab, but by a community recording demonstrations everywhere. You can now help build the dataset: build a Grabette, record tasks you are interested in, and share them on the Hub. Every episode makes the open dataset bigger and more diverse, and every contributor makes robot learning a little less gated behind expensive hardware.","This release is only the start of the project! Grabette will keep evolving. We already have more coming, including Casquette , a head-mounted POV device to complement Grabette for egocentric capture ( still a work in progress ). But the most important next step isn’t only ours, it’s also yours: start recording, and let’s build the dataset together.","👉 Build a Grabette (GitHub)：https://github.com/pollen-robotics/grabette · Process your data (HF Space)：https://huggingface.co/spaces/pollen-robotics/grabette-slam · Contribute to the dataset","Convert Grabette recordings into LeRobot SLAM dataset"],"articleImages":[{"sourceUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61324ea4e24f4931e104df67/-9VVBX72zxiB2yTDeyJnn.jpeg","alt":"","afterParagraph":0,"url":"/media/articles/cmruh5yy2040vbi07twmqcnwq/f95307d5058a64de.webp"},{"sourceUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/62f62a29d278a8f3e781e28a/5avng3ahybi8q3PatO2zv.png","alt":"","afterParagraph":0,"url":"/media/articles/cmruh5yy2040vbi07twmqcnwq/4db53bd6dce6f5fb.webp"},{"sourceUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6303eb57fc783bfc74434dd9/3nKuT_PP_gugI4Hpuu8hG.jpeg","alt":"","afterParagraph":0,"url":"/media/articles/cmruh5yy2040vbi07twmqcnwq/31153b1b158d0077.webp"}],"mediaStatus":"ok","articleBodyZh":["瓶颈不是模型，而是数据。：#the-bottleneck-isnt-the-model-its-the-data 站在UMI的肩膀上：#standing-on-the-shoulders-of-umi 认识Grabette：#meet-grabette 为所有人而建：#built-for-everyone 从你的手到数据集，仅需两步：#from-your-hand-to-a-dataset-in-two-steps 1. 记录：#1-record 2. 处理，直接在浏览器中：#2-process-directly-in-your-browser 你可以用这些数据做什么？这里有一个例子。：#what-can-you-do-with-the-data-heres-one-example 现在轮到你了：#now-its-your-turn 接下来做什么：#whats-next 使用手持抓手在几分钟内记录你自己的操作任务，将它们自动转化为机器人可用的数据集，并帮助构建一个开放的、协作的机器人学习数据集。","机器人学习面临供应问题。我们拥有强大的策略架构（基于变换器的VLA、扩散与流匹配策略，甚至世界模型）和用于训练的GPU。但我们缺乏大型、多样化的真实世界操作数据。","通过遥操作机器人来收集数据可能成本高且要求严格：首先，这需要一个机器人。并且根据遥操作方式，如果数据收集耗时数小时，还可能对用户很枯燥，并涉及大量硬件和物流挑战。这在需要各种任务和环境的情况下很难扩展。","但你并不需要机器人来收集机器人数据。只需要一只人的手、一个抓手、一台摄像机，以及恢复手部操作六自由度轨迹的方法。捕捉示范，你就得到了可以让机器人学习的数据。","这就是我们今天发布的Grabette：一个开放的、低成本的操作数据记录系统。拿起它，用自己的手记录一个任务，然后获得干净的、机器人可用的数据集。无需机器人，无需实验室，无需遥控装置。","而更大的目标是：如果记录示范和拍摄视频一样简单，任何人都可以贡献数据。我们希望Grabette能为一个大型、开放、协作的操作数据集提供种子。一个单独的实验室无法单独构建这样的大型数据集。","Grabette 直接受斯坦福大学的通用操作接口 (UMI) 启发：https://umi-gripper.github.io/：这是一种手持式抓取器，配有鱼眼摄像头，可以记录“真实环境”中的演示，利用 SLAM 恢复摄像头轨迹，并从中训练视觉运动策略。","UMI 证明了这个方法可行。其他（封闭源代码）设备也存在，比如 Agibot 的 MEgo 抓手，Genrobot 的 DAS 抓手以及 Sunday Robotics 的技能捕捉手套。我们的目标是让使用变得毫不费力，将从“我有一个任务”到“我有一个训练好的模型”的门槛降到最低。","Grabette 构建在现代开放生态系统中：LeRobot 用于数据集，Hugging Face Hub 用于共享，还有一个可以在浏览器中运行、无需安装的处理管线。Grabette 是任何人都可以在工作台上构建、在实地使用并贡献数据的工具。","我们已经开发 Grabette 数月，并且觉得它已经足够可用，可以与大家分享。我们很高兴现在可以与您分享！","Grabette 是一款手持抓手，配备了重建操作演示所需的一切设备。","它配有两台摄像头，每个摄像头有着不同的用途。角色分工是故意为之：廉价的广角鱼眼摄像头为策略提供了丰富的上下文、手腕摄像头风格的视角，而 RGBD 摄像头则承担强大的 6 自由度跟踪工作。","在 Grabette 在用户执行任务的过程中记录数据时，它依赖其机器人对应设备在训练后执行学到的动作。所以，请认识 Gripette，它是 Grabette 的机器人臂末端执行器双胞胎。","这一系列产品共享相同的硬件基因：","Grabette 手持记录设备（左）和 Gripette 机器人抓手（右）","去查看仓库吧！：https://github.com/pollen-robotics/grabette","组件。标准可购买的传感器，无封闭管线，无分支锁定。一块树莓派，标准 Pi 摄像头，一台现成的 OAK-D 深度摄像头，磁性编码器。整个意义就在于任何人都可以用可以直接订购的零件自己组装一个。","设计上与机器人无关。捕获或数据格式中没有假设特定的机械臂。演示存储为相机本地的6自由度笛卡尔位姿加夹爪状态，输出为Hugging Face Hub上的标准LeRobot数据集，因此相同的数据可以驱动不同的机器人和不同的学习方法。不过，你的机械臂上仍然需要匹配的Gripette夹爪。","此发布使任何人都能从“我想演示一个任务”快速转变为“我有一个可用于训练的数据集”，而无需先前的专业知识。","按下按钮时，观察相机、跟踪相机（彩色、深度和IMU）以及夹爪的编码器关节值会同时记录，使用单一的共享时钟以确保正确同步。再次按下按钮以停止这一回合，数据会保存在Raspberry Pi本地。","：https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/grabette/Browser_postprocess_small2.gif","在浏览器中打开Grabette仪表板。选择你想要添加到数据集的回合，一键点击即可开始后处理。","现在一切已经准备好开始训练！","一个数据集只有在可以训练某些东西时才有趣。因此，为了展示完整的循环，我们提供了一个完整的示例。但需要明确的是，这只是功能示例，而不是产品：发布的是录制系统。你的Grabette数据可以与任何使用LeRobot数据集的方法配合使用。","我们的示例采用了200个记录的演示，例如：","数据集可在该HF Dataset获取：https://huggingface.co/datasets/chouziel/dataset-cup-0107","策略可在该HF Model获取：https://huggingface.co/SteveNguyen/pick_cup_0107_smooth-best","数据瓶颈不能仅通过一个实验室解决，而是通过社区在各处录制演示来解决。你现在可以帮忙建立数据集：搭建一个Grabette，记录你感兴趣的任务，并在Hub上分享它们。每一回合都会让开放数据集更大、更丰富，而每一位贡献者都会让机器人学习稍微少一些被昂贵硬件限制的门槛。","这个发布只是项目的开始！Grabette 将会持续发展。我们已经有更多计划，包括 Casquette，一款头戴式视角设备，旨在补充 Grabette 进行自我中心的拍摄（仍在开发中）。但最重要的下一步不仅是我们的，也是你的：开始录制，让我们一起构建数据集。","👉 构建一个 Grabette（GitHub）：https://github.com/pollen-robotics/grabette · 处理你的数据（HF Space）：https://huggingface.co/spaces/pollen-robotics/grabette-slam · 为数据集做出贡献","将 Grabette 录制内容转换为 LeRobot SLAM 数据集"],"translationStatus":"translated","bodyOrigin":"source-page","editorial":{"summary":"Aioga 编辑摘要：Hugging Face 推出 Grabette，一套开源低成本系统，用户手持夹爪即可在几分钟内录制操作演示，并自动生成机器人可用的数据集。 Aioga 将其归入「产品更新」方向，重点关注它对真实使用和行业竞争的影响。","background":"背景分析：模型与研究类动态需要结合能力边界、开放方式、成本、可用性和真实任务表现判断，单项指标领先不等于已经形成稳定采用。","viewpoint":"Aioga 判断：这条动态更适合作为行业观察信号，当前信息足以建立线索，但不足以推导长期结论。","implications":"影响分析：对相关团队而言，短期应先核对来源、可用范围和实际成本，再判断是否值得接入或跟进。","nextStep":"后续观察：继续观察官方文档、实际可用性、价格变化、开发者反馈和竞品回应。","evidenceRefs":["title","summary","articleBody"],"confidence":"medium","status":"published","aiGenerated":false,"autoApproved":true,"generatedBy":"rule-safe-fallback","generatedAt":"2026-07-23T07:30:40.513Z","sourceHash":"adc13f0541c88910","validation":{"passed":true,"mode":"rule-safe-fallback","checks":["schema","length","source-attribution","no-html"]}},"tags":["产品更新","Hugging Face：Blog（RSS）"],"translations":{"zh-CN":{"title":"Hugging Face 发布 Grabette：开源手持夹爪系统，无需机器人即可录制操作数据","summary":"Hugging Face 推出 Grabette，一套开源低成本系统，用户手持夹爪即可在几分钟内录制操作演示，并自动生成机器人可用的数据集。Grabette 配备鱼眼相机与 RGBD 相机，通过 SLAM 恢复 6-DoF 轨迹，硬件物料成本约 490 欧元。所有硬件设计、处理流程与训练代码均开源，数据以标准 LeRobot 格式上传至 Hugging Face Hub，支持任意机器人后端。","category":"产品更新","source":"huggingface.co","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face 发布 Grabette：开源手持夹爪系统，无需机器人即可录制操作数据 - Aioga AI资讯","description":"Hugging Face 推出 Grabette，一套开源低成本系统，用户手持夹爪即可在几分钟内录制操作演示，并自动生成机器人可用的数据集。Grabette 配备鱼眼相机与 RGBD 相机，通过 SLAM 恢复 6-DoF 轨迹，硬件物料成本约 490 欧元。所有硬件设计、处理流程与训练代码均开源，数据以标准 LeRobot 格式上传至 Hugging Fa...","url":"https://www.aioga.com/news/cmruh5yy2040vbi07twmqcnwq/"},"en":{"title":"Hugging Face releases Grabette: an open-source handheld gripper system that can record operational data without a robot","summary":"Hugging Face has launched Grabette, an open-source, low-cost system that allows users to record operation demonstrations in a few minutes using a handheld gripper, and automatically generate datasets usable by robots. Grabette is equipped with a fisheye camera and an RGBD camera, and restores 6-DoF trajectories through SLAM, with hardware material costs of about 490 euros. All hardware designs, processing pipelines, and training code are open-source, and data is uploaded to the Hugging Face Hub in the standard LeRobot format, supporting any robot backend.","category":"Products","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face releases Grabette: an open-source handheld gripper system that can record operational data without a robot - Aioga AI News","description":"Hugging Face has launched Grabette, an open-source, low-cost system that allows users to record operation demonstrations in a few minutes using a handheld gripper, and automaticall...","url":"https://www.aioga.com/en/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:42:13.275Z"},"ja":{"title":"Hugging FaceはGrabetteを発表：ロボット不要で操作データを記録できるオープンソースの手持ちグリッパーシステム","summary":"Hugging FaceはGrabetteを発表しました。これはオープンソースの低コストシステムで、ユーザーはハンドヘルドグリッパーを使って数分で操作デモを録画し、ロボットで使用可能なデータセットを自動生成できます。Grabetteは魚眼カメラとRGBDカメラを搭載し、SLAMを通じて6自由度（6-DoF）の軌道を復元します。ハードウェアの材料費は約490ユーロです。すべてのハードウェア設計、処理フロー、トレーニングコードはオープンソースで、データは標準的なLeRobotフォーマットでHugging Face Hubにアップロードされ、任意のロボットバックエンドをサポートします。","category":"製品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging FaceはGrabetteを発表：ロボット不要で操作データを記録できるオープンソースの手持ちグリッパーシステム - Aioga AIニュース","description":"Hugging FaceはGrabetteを発表しました。これはオープンソースの低コストシステムで、ユーザーはハンドヘルドグリッパーを使って数分で操作デモを録画し、ロボットで使用可能なデータセットを自動生成できます。Grabetteは魚眼カメラとRGBDカメラを搭載し、SLAMを通じて6自由度（6-DoF）の軌道を復元します。ハードウェアの材料費は約490ユ...","url":"https://www.aioga.com/ja/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:42:24.801Z"},"ko":{"title":"Hugging Face, Grabette 발표: 로봇 없이 조작 데이터를 기록할 수 있는 오픈소스 핸드헬드 그리퍼 시스템","summary":"Hugging Face는 Grabette를 출시했으며, 이는 사용자가 그리퍼를 손에 들고 몇 분 만에 조작 시연을 녹화하고 로봇이 사용할 수 있는 데이터셋을 자동으로 생성할 수 있는 오픈 소스 저비용 시스템입니다. Grabette는 어안 카메라와 RGBD 카메라를 갖추고 있으며, SLAM을 통해 6-DoF 궤적을 복원합니다. 하드웨어 비용은 약 490유로입니다. 모든 하드웨어 설계, 처리 프로세스 및 학습 코드는 오픈 소스로 공개되어 있으며, 데이터는 표준 LeRobot 형식으로 Hugging Face Hub에 업로드되어 모든 로봇 백엔드를 지원합니다.","category":"제품 업데이트","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face, Grabette 발표: 로봇 없이 조작 데이터를 기록할 수 있는 오픈소스 핸드헬드 그리퍼 시스템 - Aioga AI 뉴스","description":"Hugging Face는 Grabette를 출시했으며, 이는 사용자가 그리퍼를 손에 들고 몇 분 만에 조작 시연을 녹화하고 로봇이 사용할 수 있는 데이터셋을 자동으로 생성할 수 있는 오픈 소스 저비용 시스템입니다. Grabette는 어안 카메라와 RGBD 카메라를 갖추고 있으며, SLAM을 통해 6-DoF 궤적을 복원합니...","url":"https://www.aioga.com/ko/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:43:18.123Z"},"es":{"title":"Hugging Face lanza Grabette: sistema de pinza de mano de código abierto, que permite grabar datos de operación sin necesidad de un robot","summary":"Hugging Face lanzó Grabette, un sistema de código abierto y bajo costo, que permite a los usuarios grabar demostraciones de operaciones en pocos minutos simplemente sosteniendo una pinza, y generar automáticamente un conjunto de datos utilizable por robots. Grabette está equipado con una cámara ojo de pez y una cámara RGBD, recupera trayectorias 6-DoF mediante SLAM, y el costo de los materiales de hardware es de aproximadamente 490 euros. Todo el diseño del hardware, los procesos de procesamiento y el código de entrenamiento son de código abierto, los datos se suben al Hugging Face Hub en el formato estándar LeRobot, y es compatible con cualquier backend de robot.","category":"Productos","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face lanza Grabette: sistema de pinza de mano de código abierto, que permite grabar datos de operación sin necesidad de un robot - Aioga Noticias de IA","description":"Hugging Face lanzó Grabette, un sistema de código abierto y bajo costo, que permite a los usuarios grabar demostraciones de operaciones en pocos minutos simplemente sosteniendo una...","url":"https://www.aioga.com/es/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:43:06.609Z"},"fr":{"title":"Hugging Face publie Grabette : système de pince portable open source, permettant d'enregistrer des données opérationnelles sans robot","summary":"Hugging Face a lancé Grabette, un système open source à faible coût, permettant aux utilisateurs de filmer une démonstration opérationnelle en quelques minutes en tenant simplement une pince, et de générer automatiquement un ensemble de données utilisable par un robot. Grabette est équipé d'une caméra fisheye et d'une caméra RGBD, et utilise le SLAM pour restaurer la trajectoire 6-DoF, le coût du matériel étant d'environ 490 euros. Tous les designs matériels, processus de traitement et codes de formation sont open source, et les données sont téléchargées au format standard LeRobot sur Hugging Face Hub, compatibles avec n'importe quel backend robotique.","category":"Produits","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face publie Grabette : système de pince portable open source, permettant d'enregistrer des données opérationnelles sans robot - Aioga Actualités IA","description":"Hugging Face a lancé Grabette, un système open source à faible coût, permettant aux utilisateurs de filmer une démonstration opérationnelle en quelques minutes en tenant simplement...","url":"https://www.aioga.com/fr/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:44:03.135Z"},"de":{"title":"Hugging Face veröffentlicht Grabette: Offenes Handgreifersystem, mit dem Bedienungsdaten ohne Roboter aufgezeichnet werden können","summary":"Hugging Face hat Grabette eingeführt, ein Open-Source-Kostensystem, mit dem Benutzer innerhalb weniger Minuten Bedienungsanleitungen aufnehmen und automatisch einen für Roboter nutzbaren Datensatz erstellen können, während sie eine Greifzange in der Hand halten. Grabette ist mit einer Fisheye-Kamera und einer RGBD-Kamera ausgestattet und rekonstruiert die 6-DoF-Trajektorie über SLAM. Die Hardwarekosten belaufen sich auf etwa 490 Euro. Alle Hardware-Designs, Verarbeitungsabläufe und Trainingscodes sind Open-Source, die Daten werden im Standard-LeRobot-Format auf den Hugging Face Hub hochgeladen und unterstützen beliebige Roboter-Backends.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face veröffentlicht Grabette: Offenes Handgreifersystem, mit dem Bedienungsdaten ohne Roboter aufgezeichnet werden können - Aioga KI-News","description":"Hugging Face hat Grabette eingeführt, ein Open-Source-Kostensystem, mit dem Benutzer innerhalb weniger Minuten Bedienungsanleitungen aufnehmen und automatisch einen für Roboter nut...","url":"https://www.aioga.com/de/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:44:01.391Z"},"pt-BR":{"title":"Hugging Face lança Grabette: sistema de garra portátil de código aberto, que permite registrar dados de operação sem a necessidade de um robô","summary":"Hugging Face lançou o Grabette, um sistema de baixo custo e código aberto, que permite aos usuários gravar demonstrações de operação em poucos minutos usando apenas uma garra manual e gerar automaticamente conjuntos de dados utilizáveis por robôs. O Grabette vem equipado com uma câmera olho de peixe e uma câmera RGBD, recuperando trajetórias 6-DoF por meio de SLAM, com um custo de materiais de hardware em torno de 490 euros. Todos os designs de hardware, fluxos de processamento e códigos de treinamento são de código aberto, os dados são enviados em formato padrão LeRobot para o Hugging Face Hub, suportando qualquer backend de robô.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face lança Grabette: sistema de garra portátil de código aberto, que permite registrar dados de operação sem a necessidade de um robô - Aioga Notícias de IA","description":"Hugging Face lançou o Grabette, um sistema de baixo custo e código aberto, que permite aos usuários gravar demonstrações de operação em poucos minutos usando apenas uma garra manua...","url":"https://www.aioga.com/pt-BR/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:44:50.263Z"},"ru":{"title":"Hugging Face выпустила Grabette: открытая система ручного захвата, позволяющая записывать данные о действиях без робота","summary":"Hugging Face представила Grabette, набор открытых и недорогих систем, который позволяет пользователям с помощью ручного захвата в течение нескольких минут записывать демонстрации операций и автоматически создавать наборы данных для роботов. Grabette оснащена рыбий глаз камерой и RGBD-камерой, восстанавливает траекторию 6-DoF с помощью SLAM, стоимость аппаратных материалов составляет около 490 евро. Все аппаратные разработки, процессы обработки и код обучения открыты, данные загружаются в стандартном формате LeRobot на Hugging Face Hub и поддерживают любую робототехническую платформу.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face выпустила Grabette: открытая система ручного захвата, позволяющая записывать данные о действиях без робота - Aioga Новости ИИ","description":"Hugging Face представила Grabette, набор открытых и недорогих систем, который позволяет пользователям с помощью ручного захвата в течение нескольких минут записывать демонстрации о...","url":"https://www.aioga.com/ru/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:44:53.078Z"},"ar":{"title":"أطلقت Hugging Face نظام Grabette: نظام قبضة محمولة مفتوح المصدر، يمكنه تسجيل بيانات التشغيل دون الحاجة إلى روبوت","summary":"أطلقت Hugging Face نظام Grabette مفتوح المصدر ومنخفض التكلفة، يمكن للمستخدمين من خلاله تسجيل عرض عملي خلال دقائق باستخدام مشبك اليد، ويتم تلقائيًا إنشاء مجموعة بيانات قابلة للاستخدام من قبل الروبوتات. يأتي Grabette مزودًا بكاميرا عين السمكة وكاميرا RGBD، ويستعيد المسار بست درجات حرية عبر SLAM، وتبلغ تكلفة المكونات المادية حوالي 490 يورو. جميع تصميمات الأجهزة، عمليات المعالجة، وشفرات التدريب مفتوحة المصدر، وتُرفع البيانات بصيغة LeRobot القياسية إلى Hugging Face Hub، مع دعم أي خلفية روبوتية.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"أطلقت Hugging Face نظام Grabette: نظام قبضة محمولة مفتوح المصدر، يمكنه تسجيل بيانات التشغيل دون الحاجة إلى روبوت - Aioga أخبار الذكاء الاصطناعي","description":"أطلقت Hugging Face نظام Grabette مفتوح المصدر ومنخفض التكلفة، يمكن للمستخدمين من خلاله تسجيل عرض عملي خلال دقائق باستخدام مشبك اليد، ويتم تلقائيًا إنشاء مجموعة بيانات قابلة للاستخد...","url":"https://www.aioga.com/ar/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:45:38.736Z"},"hi":{"title":"Hugging Face ने Grabette लॉन्च किया: ओपन-सोर्स हैंडहेल्ड ग्रिप सिस्टम, रोबोट की जरूरत नहीं, संचालन डेटा रिकॉर्ड करने के लिए","summary":"Hugging Face ने Grabette लॉन्च किया, एक ओपन-सोर्स कम लागत वाला सिस्टम, जिससे उपयोगकर्ता पिंचर पकड़कर कुछ ही मिनटों में ऑपरेशन डेमो रिकॉर्ड कर सकते हैं और यह स्वचालित रूप से रोबोट के लिए उपयोग योग्य डेटा सेट बनाता है। Grabette फिश-आई कैमरा और RGBD कैमरा से लैस है, SLAM के माध्यम से 6-DoF पथ को पुनर्निर्मित करता है, और हार्डवेयर सामग्री की लागत लगभग 490 यूरो है। सभी हार्डवेयर डिज़ाइन, प्रोसेसिंग फ्लो और प्रशिक्षण कोड ओपन-सोर्स हैं, डेटा मानक LeRobot फ़ॉर्मेट में Hugging Face Hub पर अपलोड किया जाता है, और किसी भी रोबोट बैकएंड का समर्थन करता है।","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face ने Grabette लॉन्च किया: ओपन-सोर्स हैंडहेल्ड ग्रिप सिस्टम, रोबोट की जरूरत नहीं, संचालन डेटा रिकॉर्ड करने के लिए - Aioga AI समाचार","description":"Hugging Face ने Grabette लॉन्च किया, एक ओपन-सोर्स कम लागत वाला सिस्टम, जिससे उपयोगकर्ता पिंचर पकड़कर कुछ ही मिनटों में ऑपरेशन डेमो रिकॉर्ड कर सकते हैं और यह स्वचालित रूप से रोबोट क...","url":"https://www.aioga.com/hi/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:45:43.749Z"},"it":{"title":"Hugging Face rilascia Grabette: sistema di pinza portatile open source, che consente di registrare dati operativi senza bisogno di un robot","summary":"Hugging Face ha lanciato Grabette, un sistema open source a basso costo, che permette agli utenti di registrare dimostrazioni operative in pochi minuti utilizzando una pinza manuale e di generare automaticamente un set di dati utilizzabile dai robot. Grabette è dotato di una fotocamera fish-eye e di una fotocamera RGBD, e ripristina la traiettoria a 6 gradi di libertà (6-DoF) tramite SLAM, con un costo dei materiali hardware di circa 490 euro. Tutti i progetti hardware, i processi di elaborazione e il codice di addestramento sono open source, i dati vengono caricati nel formato standard LeRobot su Hugging Face Hub e supportano qualsiasi backend robotico.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face rilascia Grabette: sistema di pinza portatile open source, che consente di registrare dati operativi senza bisogno di un robot - Aioga Notizie IA","description":"Hugging Face ha lanciato Grabette, un sistema open source a basso costo, che permette agli utenti di registrare dimostrazioni operative in pochi minuti utilizzando una pinza manual...","url":"https://www.aioga.com/it/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:46:26.489Z"},"nl":{"title":"Hugging Face lanceert Grabette: open-source handzame grijpersysteem, kan bedieningsgegevens opnemen zonder robot","summary":"Hugging Face heeft Grabette gelanceerd, een open-source en betaalbaar systeem waarmee gebruikers een handgreep kunnen vasthouden om binnen enkele minuten een demonstratie van handelingen op te nemen, en automatisch een dataset te genereren die door robots kan worden gebruikt. Grabette is uitgerust met een fisheye-camera en een RGBD-camera, en herstelt 6-DoF-trajecten via SLAM. De materiaalkosten voor de hardware bedragen ongeveer 490 euro. Alle hardwareontwerpen, verwerkingsprocessen en trainingscode zijn open source, en de gegevens worden in het standaard LeRobot-formaat geüpload naar de Hugging Face Hub, waarbij elke robotachtergrond wordt ondersteund.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face lanceert Grabette: open-source handzame grijpersysteem, kan bedieningsgegevens opnemen zonder robot - Aioga AI-nieuws","description":"Hugging Face heeft Grabette gelanceerd, een open-source en betaalbaar systeem waarmee gebruikers een handgreep kunnen vasthouden om binnen enkele minuten een demonstratie van hande...","url":"https://www.aioga.com/nl/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:46:32.048Z"},"tr":{"title":"Hugging Face, Grabette'i yayınladı: Robot gerektirmeden operasyon verilerini kaydetmeye olanak tanıyan açık kaynaklı taşınabilir kıskaç sistemi","summary":"Hugging Face, kullanıcıların birkaç dakika içinde operasyon demonstrasyonu kaydedebileceği ve robotlar için kullanılabilir veri setleri otomatik olarak oluşturabileceği düşük maliyetli açık kaynaklı bir sistem olan Grabette'i tanıttı. Grabette, SLAM ile 6-DoF (altı serbestlik derecesi) izlerini geri kazanan balık gözü kamera ve RGBD kamera ile donatılmıştır; donanım maliyeti yaklaşık 490 Euro'dur. Tüm donanım tasarımı, işleme süreci ve eğitim kodları açık kaynaklıdır, veriler standart LeRobot formatında Hugging Face Hub'a yüklenir ve herhangi bir robot arka ucunu destekler.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face, Grabette'i yayınladı: Robot gerektirmeden operasyon verilerini kaydetmeye olanak tanıyan açık kaynaklı taşınabilir kıskaç sistemi - Aioga AI Haberleri","description":"Hugging Face, kullanıcıların birkaç dakika içinde operasyon demonstrasyonu kaydedebileceği ve robotlar için kullanılabilir veri setleri otomatik olarak oluşturabileceği düşük maliy...","url":"https://www.aioga.com/tr/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:47:20.064Z"},"vi":{"title":"Hugging Face ra mắt Grabette: Hệ thống kẹp cầm tay mã nguồn mở, có thể ghi dữ liệu thao tác mà không cần robot","summary":"Hugging Face ra mắt Grabette, một bộ hệ thống mã nguồn mở chi phí thấp, cho phép người dùng cầm gắp ghi lại bản demo thao tác trong vài phút và tự động tạo ra bộ dữ liệu có thể sử dụng cho robot. Grabette được trang bị camera mắt cá và camera RGBD, phục hồi quỹ đạo 6-DoF thông qua SLAM, chi phí phần cứng khoảng 490 euro. Tất cả thiết kế phần cứng, quy trình xử lý và mã huấn luyện đều mã nguồn mở, dữ liệu được tải lên Hugging Face Hub theo định dạng chuẩn LeRobot, hỗ trợ bất kỳ nền tảng robot nào.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face ra mắt Grabette: Hệ thống kẹp cầm tay mã nguồn mở, có thể ghi dữ liệu thao tác mà không cần robot - Tin tức AI Aioga","description":"Hugging Face ra mắt Grabette, một bộ hệ thống mã nguồn mở chi phí thấp, cho phép người dùng cầm gắp ghi lại bản demo thao tác trong vài phút và tự động tạo ra bộ dữ liệu có thể sử...","url":"https://www.aioga.com/vi/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:47:23.217Z"},"id":{"title":"Hugging Face merilis Grabette: sistem cengkeraman genggam open source, dapat merekam data operasi tanpa robot","summary":"Hugging Face meluncurkan Grabette, sebuah sistem open-source berbiaya rendah, yang memungkinkan pengguna merekam demonstrasi operasi dalam beberapa menit hanya dengan memegang penjepit, dan secara otomatis menghasilkan dataset yang dapat digunakan oleh robot. Grabette dilengkapi dengan kamera fisheye dan kamera RGBD, memulihkan jejak 6-DoF melalui SLAM, dengan biaya bahan perangkat keras sekitar 490 euro. Semua desain perangkat keras, proses pengolahan, dan kode pelatihan bersifat open-source, data diunggah dalam format LeRobot standar ke Hugging Face Hub, dan mendukung backend robot apa pun.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face merilis Grabette: sistem cengkeraman genggam open source, dapat merekam data operasi tanpa robot - Berita AI Aioga","description":"Hugging Face meluncurkan Grabette, sebuah sistem open-source berbiaya rendah, yang memungkinkan pengguna merekam demonstrasi operasi dalam beberapa menit hanya dengan memegang penj...","url":"https://www.aioga.com/id/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:48:03.647Z"},"th":{"title":"Hugging Face เปิดตัว Grabette: ระบบกรงเล็บมือถือแบบโอเพนซอร์ส บันทึกข้อมูลการปฏิบัติงานได้โดยไม่ต้องใช้หุ่นยนต์","summary":"Hugging Face เปิดตัว Grabette ระบบโอเพ่นซอร์สราคาประหยัด ผู้ใช้สามารถถือกรงเล็บแล้วบันทึกการสาธิตการปฏิบัติงานภายในไม่กี่นาที และสร้างชุดข้อมูลที่หุ่นยนต์สามารถใช้ได้โดยอัตโนมัติ Grabette มาพร้อมกล้องฟิชอายและกล้อง RGBD ใช้ SLAM ฟื้นฟูเส้นทาง 6-DoF ต้นทุนวัสดุฮาร์ดแวร์ประมาณ 490 ยูโร การออกแบบฮาร์ดแวร์ทั้งหมด กระบวนการประมวลผล และโค้ดการฝึกอบรมทั้งหมดเป็นโอเพ่นซอร์ส ข้อมูลจะถูกอัปโหลดในรูปแบบ LeRobot มาตรฐานไปยัง Hugging Face Hub รองรับแบ็คเอนด์ของหุ่นยนต์ทุกชนิด","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face เปิดตัว Grabette: ระบบกรงเล็บมือถือแบบโอเพนซอร์ส บันทึกข้อมูลการปฏิบัติงานได้โดยไม่ต้องใช้หุ่นยนต์ - ข่าว AI Aioga","description":"Hugging Face เปิดตัว Grabette ระบบโอเพ่นซอร์สราคาประหยัด ผู้ใช้สามารถถือกรงเล็บแล้วบันทึกการสาธิตการปฏิบัติงานภายในไม่กี่นาที และสร้างชุดข้อมูลที่หุ่นยนต์สามารถใช้ได้โดยอัตโนมัติ G...","url":"https://www.aioga.com/th/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:48:16.560Z"},"pl":{"title":"Hugging Face wydaje Grabette: otwartoźródłowy system chwytaków ręcznych, który pozwala na nagrywanie danych operacyjnych bez potrzeby użycia robota","summary":"Hugging Face wprowadza Grabette, zestaw niskokosztowego systemu open-source, dzięki któremu użytkownicy mogą w ciągu kilku minut nagrać demonstrację działania za pomocą chwytaka i automatycznie wygenerować przydatny dla robotów zbiór danych. Grabette wyposażone jest w kamerę rybie oko oraz kamerę RGBD, odzyskując 6-stopniową trajektorię ruchu za pomocą SLAM, a koszt materiałów sprzętowych wynosi około 490 euro. Wszystkie projekty sprzętu, procesy przetwarzania i kody treningowe są open-source, a dane w formacie standardowym LeRobot są przesyłane na Hugging Face Hub, obsługując dowolny backend robota.","category":"产品更新","source":"Hugging Face：Blog（RSS）","aggregationSource":"Hugging Face：Blog（RSS）","pageTitle":"Hugging Face wydaje Grabette: otwartoźródłowy system chwytaków ręcznych, który pozwala na nagrywanie danych operacyjnych bez potrzeby użycia robota - Aioga Wiadomości AI","description":"Hugging Face wprowadza Grabette, zestaw niskokosztowego systemu open-source, dzięki któremu użytkownicy mogą w ciągu kilku minut nagrać demonstrację działania za pomocą chwytaka i...","url":"https://www.aioga.com/pl/news/cmruh5yy2040vbi07twmqcnwq/","contentTranslated":true,"sourceHash":"ccfdd12e1294ddcc","translatedAt":"2026-07-23T03:49:03.646Z"}}}}