Wristband enables wearers to control a robotic hand with their own movements

2026-03-25 · Source: MIT News - Artificial intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems, Emerging Technologies & Innovation · Depth: Advanced, medium

Summary

MIT engineers have developed an ultrasound wristband that precisely tracks hand movements in real-time, as detailed in a March 25, 2026, paper in *Nature Electronics*. This device generates ultrasound images of the wrist's muscles, tendons, and ligaments, which an integrated artificial intelligence algorithm continuously translates into the corresponding positions of the five fingers and palm. The wristband can be trained to learn a wearer's specific hand motions and wirelessly communicate these to a robotic hand or a virtual environment. Demonstrations include controlling a robot to play piano or shoot a basketball, and manipulating virtual objects on a screen. This technology aims to overcome limitations of camera-based or sensor-glove systems, offering a more natural and precise method for capturing human dexterity for applications in robotics training and virtual/augmented reality.

Key takeaway

For AI Scientists developing dexterous robotic systems or advanced human-computer interfaces, this ultrasound wristband offers a novel, high-fidelity input method. You should consider integrating this wearable imaging approach to capture nuanced hand movements, potentially replacing less precise camera or glove-based systems. This could significantly enhance training data for humanoid robots and enable more intuitive control in virtual reality applications.

Key insights

An ultrasound wristband combined with AI precisely tracks hand movements for robotic control and virtual interaction.

Principles

• Wrist tendon states correlate to hand positions.
• Ultrasound imaging offers continuous, dexterous tracking.

Method

The method involves an ultrasound wristband imaging wrist muscles and tendons, paired with an AI algorithm trained to correlate these images with 22 degrees of freedom in hand movements, enabling real-time translation.

In practice

• Control robotic hands wirelessly.
• Manipulate virtual objects in VR/AR.
• Generate data for humanoid robot training.

Topics

• Ultrasound Wristband
• Hand Tracking
• AI Algorithms
• Robotics Control
• Virtual Reality

Best for: AI Scientist, AI Engineer, Robotics Engineer, Research Scientist

Related on AIssential

• AVI-HT: Adaptive Vision-IMU Fusion for 3D Hand Tracking — Adaptive fusion of egocentric vision and on-glove 6-DoF IMUs, guided by cross-sensor attention, significantly improves 3D hand tracking under occlusion.
• Monocular Markerless Motion Capture Enables Quantitative Assessment of Upper Extremity Reachable Workspace — Monocular AI-driven markerless motion capture offers a clinically viable, low-overhead method for upper extremity reachable workspace assessment.
• VEPHand: View-Efficient Photometric Hand Performance Capture at Scale — VEPHand enables robust, high-fidelity 3D hand capture and registration from ~20 unmasked views, using neural reconstruction and physics-inspired deformation modeling.
• Efficient Sensor Fusion for Gesture Recognition on Resource-Constrained Devices — Sensor fusion of low-resolution ToF and IR enables efficient, private gesture recognition on resource-constrained devices.
• [AINews] Midjourney Medical: scan your organs like you step on a scale — Midjourney is pioneering a full-body ultrasonic CT system for accessible, frequent personal health monitoring.
• CHOIR: Contact-aware 4D Hand-Object Interaction Reconstruction — CHOIR reconstructs 4D hand-object interactions from monocular video, explicitly using contact as a coupling signal for improved consistency.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by MIT News - Artificial intelligence.