← All stories
● Covered by 1 source · 1 reportLow impact1 neutral

Axonnic (YC F26) develops forearm sleeve for tracking finger movements and force

🔄 Updated 5d ago
New to BrevFeed? We gather this story from every outlet covering it into one summary — ranked by real-world impact, not just the latest headline — so you never miss what matters. What is BrevFeed? →

Key points

  • Forearm sleeve tracks finger movements and estimates fingertip force.
  • Uses 64-channel surface electromyography (EMG).
  • Generates training data for dextrous robots.
  • Achieved 6.9° error across 20 joint angles in tests.
  • Developing custom electronics for improved reliability.

Sleeve Technology for Robot Training

Axonnic has introduced a forearm sleeve that utilizes electromyography (EMG) to decode finger movements and estimate fingertip force. The sleeve leaves the hands bare while collecting data on muscle activity. This system is intended for recording human movement to create training data for dextrous robots.

EMG vs. Video Tracking

The company states that EMG provides a more effective method for training robots compared to video alone. Video primarily captures movement, whereas EMG detects muscle activity and the effort behind movements, even when hand motion is minimal. This allows for the capture of subtle muscle movements crucial for tasks like sewing and delicate assembly.

Technical Implementation and Performance

The sleeve incorporates 64 channels of surface EMG, with electrodes distributed across the forearm to detect electrical activity from muscles. The system synchronizes EMG data with hand tracking to train a model that predicts finger joint angles. Fingertip force estimates are calibrated using finger presses on force sensors. In a test conducted four days after training without recalibration, the system showed a 6.9° error across 20 joint angles when compared to Apple Vision Pro hand tracking.

Addressing Data Collection Challenges

Axonnic encountered issues with wireless interference and unreliable off-the-shelf hardware during factory recordings, leading to poor data quality. To resolve these problems, the company is developing its own wired PCB electronics. This custom hardware aims to eliminate interference and timing inconsistencies, improving data collection reliability.

Origin and Application Focus

The technology originated from EMG research at Oxford. While initially considered for computer control, Axonnic shifted its focus to capturing the effort involved in skilled manual tasks. This approach allows computers to gain insights and learn from human skills, particularly in areas like sewing where material deformation and constant grip adjustments are common.

✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →

The daily brief

One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.

One email a day. Unsubscribe in one click, any time.

Today's brief

Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.

~4 min · 3 stories · Nov 21

▶ Play today's brief Listen on Spotify

New every morning, and the back catalogue is archived by date.

Primary sources

GitHub HackerNews/API

Reporting from

Axonnic, a Y Combinator-backed startup, has developed a forearm sleeve that uses electromyography (EMG) to track finger movements and estimate fingertip force. This technology is designed to record human movement and generate training data for dextrous robots, offering a more detailed signal than video-based tracking.