Technology1 min read

Launch HN: Axonnic (YC F26) – Sleeves that track fingers and estimate force

By · Published by Everything Blog

In short

The wearable system uses 64 channels of surface electromyography placed across the forearm to decode joint angles and estimate fingertip forces through a synchronized machine learning model. During an evaluation four days post-training with zero recalibration, the sleeve demonstrated an average error of only 6.9 degrees across 20 joint angles compared to Apple Vision Pro tracking. The team is now transitioning to a custom wired PCB design to eliminate wireless interference discovered during real-world factory trials. Axonnic is currently conducting industrial pilots while expanding its training datasets across manufacturing and construction trades.

Key points

  • The bare-hand wearable design captures nuanced grip pressure and joint motion that tradit…: The bare-hand wearable design captures nuanced grip pressure and joint motion that traditional optical tracking cannot register.
  • Factory reliability and interference challenges prompted the team to shift toward a custo…: Factory reliability and interference challenges prompted the team to shift toward a custom wired printed circuit board.
  • Industrial validation is underway through a letter of intent with a European manufacturer…: Industrial validation is underway through a letter of intent with a European manufacturer alongside field data collection in construction.

Sources checked by our analysis pipeline: 1

Hi HN! We’re Arsh and Max, founders of Axonnic (

https://axonnic.com). We’ve developed a forearm sleeve that reads muscle activity to decode finger movements and estimate fingertip force, while leaving the hands bare. It’s used to record human movement and generate training data for dextrous robots.

Here’s a demo video: https://youtube.com/shorts/xBrocTc9cfA

We’ve found that electromyography (EMG) is a much better way to train robots than by video alone because video only captures movement, not muscle activity or the effort behind the movement. A useful signal can be present even when the hand barely moves; just maintaining a grip involves muscle activation. The subtle muscle movements that can barely be picked up in video are the most important details for activities like sewing and delicate assembly.

The sleeve has 64 channels of surface electromyography, or EMG. Electrodes on the skin detect electrical activity from muscles in the forearm. We distribute sensors across the forearm so as to not overfit to one muscle group. We synchronize EMG with hand tracking to train a model that predicts finger joint angles, then we run…

Technology