88Z AI, 17 November — YC F26 batch startup Axonnic has launched a forearm sleeve that decodes finger movements and estimates fingertip force by reading muscle activity. The device aims to address the limitations of video-only robot training, offering a new solution for generating high-quality training data for dexterous robots.
At a glance
- Axonnic's sleeve decodes finger movements and estimates fingertip force via EMG, addressing gaps in video-only data.
- The technology provides high-quality training data with force awareness for dexterous robots, enhancing their manipulation capabilities.

Technology and Functionality
Axonnic's forearm sleeve decodes specific finger movements and estimates fingertip force by monitoring muscle activity, all while keeping the hands bare. This non-invasive design allows users to operate naturally while capturing detailed biomechanical signals.
Application Value and Advantages
The founders note that training robots solely on video data is limited, as video only records surface movement without capturing underlying muscle activity or effort. In contrast, electromyography (EMG) signals provide useful information even when the hand is nearly static, offering richer and more accurate training data for dexterous robots to enhance their manipulation precision and force control.
Sources & editorial note
This article is an AI-assisted synthesis by 88Z AI based on the public sources below. Product claims and availability are attributed to their publishers. It does not represent independent testing or first-hand reporting.
- news.ycombinator.comSource published
Source dates above refer to the original announcements; the date under the headline is this article’s publication on 88Z AI.