{"product_id":"dobot-pocketgo-data-collection-platform","title":"Dobot PocketGo Data Collection Platform","description":"\u003cp\u003eThe Dobot PocketGo collects robot training data without the robot. An operator performs a task with a handheld gripper that carries a camera, wherever the task happens, and the system records what the gripper saw and exactly how it moved. A matching gripper on a Dobot arm then uses that data to learn and repeat the skill, following the behaviour cloning approach of research systems such as UMI.\u003c\/p\u003e\u003cp\u003eThe kit holds two gripper sets, one handheld for recording and one robot-mounted for running policies, with the same camera viewpoint and finger design so that what a model learns from people carries over to the robot. Recording runs through a GoPro Hero 12 at 5.3K and 60 fps, with a 155° field of view, HyperSmooth 6.0 stabilisation and a built-in IMU. Visual-inertial SLAM based on ORB-SLAM3 tracks the gripper's 6D pose and annotates each session automatically.\u003c\/p\u003e\u003cp\u003eThe software covers the full pipeline: collection, calibration, SLAM trajectory processing, training and deployment, with a secondary development SDK and a Docker environment for custom research. Dobot rates throughput at up to 4,000 demonstrations a day, depending on task length and workflow, and the gripper handles objects up to 2 kg.\u003c\/p\u003e\u003cp\u003eDeployment needs a Dobot Nova or CR series arm, sold separately. Training needs a GPU: the optional mini AI computer (Intel i9 with an RTX GPU of 11 GB VRAM or more) or your own workstation. High-resolution video from thousands of demonstrations also needs plenty of storage.\u003c\/p\u003e\u003ch3\u003eKey Capabilities\u003c\/h3\u003e\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eCollect Without the Robot:\u003c\/strong\u003e The handheld gripper records demonstrations at a bench, in a kitchen or in a warehouse aisle.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eSame View for Human and Robot:\u003c\/strong\u003e Handheld and robot-mounted grippers share the camera viewpoint and finger design.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e5.3K Wide-Angle Video:\u003c\/strong\u003e A GoPro Hero 12 records at 60 fps with a 155° field of view and a built-in IMU.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e6D Pose Tracking:\u003c\/strong\u003e Visual-inertial SLAM based on ORB-SLAM3 tracks the gripper and annotates each session.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eData to Deployment:\u003c\/strong\u003e The software runs collection, calibration, training and deployment, with an SDK and Docker environment.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eUp to 4,000 Demonstrations a Day:\u003c\/strong\u003e Dobot rates that throughput for a fast workflow, depending on the task.\u003c\/li\u003e\n\u003c\/ul\u003e\u003ch3\u003eBuying through Robotix Market\u003c\/h3\u003e\u003cp\u003eThis unit is sourced new through established distribution channels and ships worldwide with the manufacturer warranty. Technical support is coordinated with the manufacturer's own service network. Deployment scope and configuration are agreed before dispatch, and on-site installation is not included in the product price.\u003c\/p\u003e","brand":"Dobot","offers":[{"title":"Default Title","offer_id":67873543487778,"sku":"Dobot-1200000404","price":5875.0,"currency_code":"CHF","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1022\/0693\/1234\/files\/dobot-pocket-go-_1200000404.jpg?v=1795145637","url":"https:\/\/robotixmarket.ch\/en\/products\/dobot-pocketgo-data-collection-platform","provider":"Robotix Market Europe","version":"1.0","type":"link"}