Pollen Robotics Releases Grabette, an Open Handheld System for Robot-Manipulation Data Collection

Pollen Robotics Releases Grabette, an Open Handheld System for Robot-Manipulation Data Collection Pollen Robotics has introduced Grabette, an open-source, low-cost handheld gripper designed to record real-world manipulation tasks without requiring a robot or teleoperation rig. The system aims to address robot learning's data bottleneck by converting handheld human demonstrations directly into robot-ready datasets shared via the Hugging Face ecosystem. Grabette is a handheld demonstration device equipped with a Raspberry Pi, a wide fisheye camera, an OAK-D depth camera, and magnetic encoders, with a bill of materials (BOM) cost of roughly €490. Gripette serves as Grabette's motorized robot-arm counterpart with a BOM of approximately €120, using two servomotors to replicate trained tasks on real or simulated arms. Demonstrations are processed browser-side via a Hugging Face Space using RTAB-MAP SLAM to recover 6-DoF trajectories and convert recordings into standard LeRobot datasets. Pollen Robotics also revealed ongoing development of Casquette, a head-mounted point-of-view device for complementary egocentric data capture. Hardware Design and Paired Gripper Inspired by Stanford's Universal Manipulation Interface (UMI), Grabette replaces complex teleoperation rigs with off-the-shelf components. The handheld recording device splits duties between a wide fisheye lens for observation context and an OAK-D RGBD camera with an IMU for robust 6-DoF SLAM tracking. For downstream execution, it pairs with Gripette, a motorized end-effector twin intended to be mounted on a robotic arm like the OpenArm. Workflow and Open Ecosystem Integration Data capture is handled via a single-button control on a Raspberry Pi that records synchronized video, depth, IMU, and encoder values. Through an online browser dashboard hosted on Hugging Face Spaces, users upload episodes for trajectory verification with the RTAB-MAP SLAM library and format conversion into standard LeRobot datasets. The resulting 6-DoF cartesian pose and gripper data can then be used to train models such as Diffusion Policies on consumer GPUs.

Pollen Robotics 推出开源低成本机器人操作数据采集系统 Grabette 为解决机器人学习中真实操作数据匮乏的问题，Pollen Robotics 发布了受斯坦福 UMI 启发的开源低成本系统 Grabette。用户无需实体机器人或遥操作设备，仅通过手持式夹爪即可记录人类示范，并能直接在浏览器中自动处理生成可用于训练的 LeRobot 格式数据集。 Grabette 是一款成本约 490 欧元的开源手持示范装置，配套成本约 120 欧元的机械臂末端夹爪 Gripette。 硬件搭载树莓派、用于观察环境的广角鱼眼相机、用于 6 自由度跟踪的 OAK-D 深度相机及磁编码器。 两步式工作流：一键同步采集传感器数据并保存在树莓派，通过浏览器 Hugging Face Space 调用 RTAB-MAP 库运行 SLAM 并自动转换为 LeRobot 数据集。 采集数据与机器人本体无关（Robot-agnostic），示范数据可直接用于 LeRobot 框架下的扩散策略训练并在 OpenArm 机械臂上评测。 硬件架构与设计理念 Grabette 的设计灵感来自斯坦福大学的 UMI。为消除昂贵遥操作硬件的门槛，系统将传感器集成于手持夹爪中：广角鱼眼相机提供类似腕部视角的丰富上下文，OAK-D RGBD 相机负责 6 自由度轨迹跟踪，所有元器件均为标准市售零件，物料清单成本约 490 欧元。训练完成后，则由其硬件孪生设备——带双伺服电机的电动夹爪 Gripette（成本约 120 欧元）安装在机械臂末端负责执行。 数据采集与浏览器端自动化处理 系统采集过程分为两步：用户按键开始示范，系统依托统一时钟同步记录观察画面、跟踪相机数据及夹爪编码器开合状态，停止后保存在板载树莓派中；随后用户在浏览器控制台上传数据，部署在 Hugging Face Space 的服务通过 RTAB-MAP 库执行 SLAM 并校验轨迹连续性，最终自动转换并导出为标准的 LeRobot 数据集格式。 端到端训练验证与社区演进 示范数据保存为相机局部的 6 自由度笛卡尔位姿与夹爪状态，具备机械臂通用性。官方通过 200 次示范展示了完整链路：在消费级 GPU 上利用 LeRobot 训练基于 ResNet18 和 SpatialSoftmax 编码器的扩散策略，并在搭载 Gripette 的 OpenArm 7 自由度机械臂上验证成功。此外，团队正开发头戴式第一人称视角设备 Casquette，以扩展以自我为中心的演示采集能力。

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. The bottleneck isn’t the model. It’s the data. 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. Standing on the shoulders of UMI Grabette is directly inspired by the Universal Manipulation Interface (UMI) 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. Meet Grabette 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, the handheld demonstration device (camera + IMU + gripper, BOM cost ~490€) Gripette, the motorized gripper (camera + two servomotors, BOM cost ~120€) that closes the loop on a real or simulated robot arm Grabette hand held recording device (left) and Gripette robot gripper (right) Built for everyone Everything is open source Go check the repository! Hardware : CAD and production files for Grabette and Gripette Capture service : the on-device Raspberry Pi software Processing pipeline : run locally, or online via our Hugging Face Space Example downstream stack : stock LeRobot training + the OpenArm evaluation, as a reference 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. From your hand to a dataset, in two steps 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. 1. Record 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. 2. Process, directly in your browser Open the Grabette dashboard in your browser. Select the episodes you want to add to the dataset, and with one click, post-processing begins. The episodes are uploaded to the HF Hub The grabette-slam space performs SLAM using RTAB-MAP library and verifies that the trajectory is correct (with no jumps or loss of tracking) The episodes are converted to LeRobot format A new dataset is uploaded to your space, where you can view the data for each episode using the Le Robot visualizer Everything is now ready to start training! What can you do with the data? Here’s one example. 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 : and: Trains a policy with the LeRobot stack — a Diffusion Policy (ResNet18 + SpatialSoftmax encoder, DDIM scheduler, 6-D rotation actions) that fits on a single consumer GPU. Evaluates it on a OpenArm 7-DoF arm with the Gripette gripper, driven over a gRPC API, with this result : Now it's your turn 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. What's next 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) · Process your data (HF Space) · Contribute to the dataset Built with ❤️ by Pollen Robotics.