Article

OpenJaws: An open-source hardware UMI framework for generalist manipulation, using stereo localization to improve demonstration accuracy

OpenJaws is a fully open-source sensorized UMI hardware and software framework that pairs a modular 3D-printed gripper with a low-cost stereo camera to recover metric camera trajectories, improving action-label localization accuracy in handheld demonstrations. The authors also propose UMI-Loc-Bench-v1, a benchmark for quantifying the real-world localization accuracy of handheld data-collection devices, and show that stereo localization clearly outperforms monocular alternatives. Policies trained on data collected with OpenJaws have been deployed on real robots across multiple tasks, and the hardware, software, and data are released under a commercially friendly license.

Part of the event: OpenJaws: Open-Source UMI Hardware and Stereo Localization Framework

This page provides a summary and source link only.