Mantis UMI Announced: Handheld Bimanual Grippers Accelerate Embodied AI Data Collection
chris_j_paxton · x · 2026-08-11
Almond Robotics announced Mantis UMI, a pair of handheld data collection grippers designed for physical AI (embodied AI) teams.
The device can collect accurate bimanual manipulation data in the real world 10x faster than traditional teleoperation. Mantis uses the exact same grippers as the Axol robot, ensuring seamless transfer from data collection to execution. It supports open-source software and modular trackers (like Vive Tracker, Quest controllers) and is available today.
More from Embodied
- MemoMind Smart Glasses Exceed Kickstarter Goal 100x, Raise ~$9M — chrisgrayson · 2026-08-11
- Mocking the Embodied AI Boom: Waking Up to 23 Robotics News and 42 Funding Rounds — lukas_m_ziegler · 2026-08-11
- Why Human-Hand Data is the Key to Robot Scaling Laws — JasonMa2020 · 2026-08-11
- Dyna-2: Robot Foundation Model Trained on 1M+ Hours of Human Data Reveals New Scaling Law — JasonMa2020 · 2026-08-11
- University of Tokyo's DRAGON: A Transformable Flying Robot That Acts as a Manipulator — acmoytoy · 2026-08-11
- DynaRobotics Unveils Industry-First Scaling Law Linking Human Video to General Robot Capabilities — JasonMa2020 · 2026-08-11