Skip to main content
BL

Blomega Lab

Blomega Lab builds wearable motion‑capture hardware for robotics developers, offering a 32‑DoF glove with per‑finger force sensing and a full‑body suit that provides high‑frequency (240 Hz) multimodal data streams. Their pipeline captures natural human movement, retargets the kinematics to any robot, and integrates with training frameworks like Isaac Lab and LeRobot, enabling developers to train and deploy dexterous policies directly on their robots.

Updated 29 days ago

Funding

Funding not disclosed

Funding rounds are not available yet.

Founders

Founder details are not available yet.

Product

Problem

Robotics developers lack high‑frequency, multimodal human motion and force data needed to train dexterous control policies, because existing solutions rely on vision systems that miss force information, teleoperation that is slow, or simulations that are overly clean.

Solution

Blomegalab offers a wearable full‑body suit combined with a glove system that captures human kinematics and per‑gram force data at 240 Hz. The hardware provides 32 degrees of freedom per finger, integrated force sensing, and haptic feedback, enabling precise retargeting of human movements onto robots. Data streams directly to developers’ pipelines for use in training environments such as Isaac Lab or custom stacks, and the resulting policies can be deployed to autonomous robots for more natural teleoperation and data‑driven dexterous control. The wireless, camera‑free design allows developers to capture motion anywhere without complex setup.

Target Audience

Primary customers are robotics developers, research labs, and companies building teleoperation or dexterous manipulation systems that require high‑resolution human motion and force datasets.

Features

  • Full‑body suit and glove ensemble delivering 32 DOF per finger with per‑gram force sensing
  • Integrated haptic feedback for realistic interaction during data capture
  • High‑frequency 240 Hz multimodal data streaming to user‑defined storage buckets
  • End‑to‑end pipeline: capture → retarget human kinematics to robot → train in simulation platforms → deploy policies to hardware
  • Wireless, snap‑on form factor eliminates the need for external cameras or stationary rigs
  • Compatibility with popular robotics frameworks (e.g., Isaac Lab, LeRobot) and custom pipelines
This profile is AI-generated and may contain inaccuracies.