Encord, the data infrastructure company for Physical AI, has released EMG-1, the largest open-source dataset pairing muscle signals to first-person video. Developed in collaboration with Wearable Devices, the release ties biological signals to AI development, using wristbands that read forearm muscle signals behind every finger movement, a technique called electromyography or EMG, capturing what hand is doing even when hidden from view.
Autonomous robots learn how to manipulate objects in deployment by training on real-world video of people completing tasks, but cameras lose track of hands when occluded, most often by object being handled. EMG is used to produce accurate hand-pose labels on training data where camera fails, continually recording electrical activity that drives each finger. Paired with first-person video, two streams provide complete record of movement inaccessible through camera alone, plus signals like force and contact camera cannot capture.
Experiments showed combining EMG with video reduced fingertip tracking error by 25% compared with video alone, and resulted in 35% lower error during short gaps in visual tracking. EMG alone also recognized pinch-like finger movements.
EMG is first of several biological signals Encord Data Labs is bringing into robot training data. Lab also conducting research into how brain signals EEG can be used to label operator's mental state such as satisfaction or error response and steer robot policies.
"We work with hundreds of companies at the frontier of Physical AI like Toyota, Boston Dynamics and Zipline, and it's clear that real-world model performance comes down to the data going in. With EMG-1 and our new state-of-the-art hand-tracking model, Encord is offering a solution to one of the biggest problems facing robotics teams today," said Eric Landau, Co-Founder and Co-CEO of Encord.
Introducing Encord Data Labs
EMG-1 releases in conjunction with launch of Encord Data Labs, research division working at frontier of Physical AI data development. Alongside EMG-1, Data Labs also releasing Encord-REACH new state-of-the-art hand-tracking model built for real-world conditions improving wrist errors by 80%, joints by 65%, and industrial glove errors up to 70%. Also synthetic data generation findings in collaboration with NVIDIA and ANYbotics generating rare industrial anomalies like liquid spills improving recall on real-world anomalies by up to 24%.
"This week, the people building the most ambitious robots in the world saw EMG-1 and our hand tracking running in real time," said Ulrik Stig Hansen, Co-Founder and Co-CEO of Encord. "Data Labs is the home of Encord's research at the frontier of Physical AI. We're just getting started."
About Encord
The company supports over 300 AI teams globally including Woven by Toyota, Boston Dynamics and Zipline and has seen significant growth in both revenue and data volume as result of surge in Physical AI.
