Axonnic Introduces Forearm EMG Sleeves to Translate Human Dexterity into Robot Training Data
Startup Axonnic has unveiled a 32-channel electromyography sleeve designed to record physical gestures, finger movement, and grip force to train industrial robots.
Photo: Hacker News Front Page
Key points
- Axonnic launched a 32-channel forearm EMG sleeve to capture muscle signals and force for robot training.
- The hardware operates without cameras or restrictive gloves, tracking finger movements and grip pressure.
- Target industries include delicate manufacturing, such as industrial sewing, as well as construction trades.
A new hardware startup named Axonnic has launched a specialized forearm sleeve that captures electrical muscle signals, finger positions, and fingertip pressure in real time. Unlike optical systems or bulky data gloves, the fabric sleeve leaves the human hand completely unobstructed while tracking detailed physical exertion that cameras typically fail to capture.
The company aims to help manufacturers automate complex, dexterous operations by recording how skilled workers perform manual tasks. By capturing 32-channel EMG data sampled at 2,048 Hz alongside video and hand poses, Axonnic builds task-specific datasets. Proprietary physics-based AI models then retarget these human motion recordings into action spaces suitable for robotic hardware.
Axonnic reports that its technology is already being deployed across multiple sectors, noting a letter of intent from a European manufacturer dealing with delicate sewing tasks, as well as trials with construction trades like electricians and plumbers. The hardware is priced at $10,000 per sleeve or $20,000 for a pair, with a discounted rate available for bulk orders.
Technical Specifications and Pricing
- Sensing method: 32-channel forearm EMG at 2,048 Hz.
- Re-calibration: Under a minute of movement following re-donning.
- Pricing: $10,000 per sleeve when purchased individually, or $8,000 per sleeve when bought in pairs for Gen 2 hardware.
"Video tells you where the hand moved. EMG gives another signal for what the human was physically doing to make that movement happen — muscle activation, inferred effort, the preparation before contact."
What to watch next: Whether industrial manufacturers adopt muscle-signal tracking widely to overcome the limitations of computer vision in robotic automation.
Source Hacker News Front Page — axonnic.com/ ↗
Read next
⚖️Regulation & PolicyOpenAI Partners with Chilean Ministry to Advance Public Sector AI
OpenAI has signed a non-binding agreement with Chile's science ministry to integrate artificial intelligence into public administration and support local startups.
🌐Work & SocietyAmbience Healthcare Expands Clinical AI Suite for Hospital Operations
Ambience Healthcare has launched new AI tools designed to assist hospital staff with patient rounding and discharge planning, aiming to improve both clinical efficiency a…
🧠AI AnalysisAI Models Vulnerable to Manipulation in Simulated Warfare Scenarios, Research Shows
New research reveals that leading AI models from firms like OpenAI and Anthropic can be manipulated into identifying civilian targets when prompted with game scenarios.
⚖️Regulation & PolicyAWS Highlights Enterprise Governance and AI Workspace Quick Ahead of re:Invent 2026
Amazon Web Services is spotlighting its workplace AI platform, AWS Quick, ahead of its upcoming re:Invent 2026 conference, emphasizing secure deployment across major ente…
🏢Big TechLoanPro Integrates Amazon Bedrock to Automate Loan Servicing Workflows
LoanPro has deployed a multi-agent AI assistant using Amazon Bedrock and Anthropic's Claude models to help lenders manage borrower accounts, resulting in a 15% reduction …
🏢Big TechGoogle Brings Wallet App to iOS Users Across the United States
Google has expanded the availability of its Wallet application to iOS devices in the U.S., allowing Apple users to store digital passes, tickets, and receipts.