Posted in | News | Medical Robotics

Pressure Sensors Give Robotic Prosthetic Better Grip

A new AI-powered prosthetic hand takes the guesswork out of gripping, helping users handle delicate and rigid objects with confidence.

A robotic hand wearing a blue vinyl glove squeezes a range of objects, including a camera and a drinks can.
Pressure sensors are placed at the fingertips of the prosthetic hand, and a camera near its palm (left). The prosthetic hand was tested on a can, an egg, and a USB stick (right). Image Credit: Li et al.

Recently published in Nanotechnology and Precision Engineering, researchers from Guilin University of Electronic Technology in China have developed an object identification system for prosthetic hands that helps determine the appropriate grip strength in real time.

Handling eggs requires delicacy: Apply too much pressure, and they crack. But to open a water bottle, a huge amount of grip strength and pressure is needed. 

There are approximately 50,000 new amputations each year in the United States, according to the U.S. Centers for Disease Control and Prevention. The loss of a hand can be especially challenging, hindering individuals’ capacity to carry out daily activities.

A major user-experience issue with prosthetic hands is the need to accurately adjust the grip strength according to the object being manipulated.

We want to free the user from thinking about how to control [an object] and allow them to focus on what they want to do, achieving a truly natural and intuitive interaction.

Hua Li, Study Author, School of Life and Environmental Sciences, Guilin University of Electronic Technology

Pens, cups, bottles, balls, metal sheet items such as keys, and delicate objects like eggs constitute more than 90 % of the various items that disabled patients use on a daily basis.

The researchers assessed the grip strength required to handle these everyday items and input these measurements into a machine learning-driven object identification system, which employs a small camera positioned near the palm of the prosthetic hand.

The system incorporates an electromyography (EMG) sensor located on the user’s forearm to ascertain the user’s intended action with the object in their grasp.

An EMG signal can clearly convey the intent to grasp, but it struggles to answer the critical question, how much force is needed? This often requires complex training or user calibration. Our approach was to offload that ‘how much’ question to the vision system.

Hua Li, Study Author, School of Life and Environmental Sciences, Guilin University of Electronic Technology

The team intends to incorporate haptic feedback into their system, offering users an intuitive physical sensation that can create a two-way communication link between the user and the hand through supplementary EMG signals.

What we are most looking forward to, and currently focused on, is enabling users with prosthetic hands to seamlessly and reliably perform the fine motor tasks of daily living. We hope to see users be able to effortlessly tie their shoelaces or button a shirt, confidently pick up an egg or a glass of water without consciously calculating the force, and naturally peel a piece of fruit or pass a plate to a family member.

Hua Li, Study Author, School of Life and Environmental Sciences, Guilin University of Electronic Technology

Journal Reference:

Li, Y., et al. (2026). An intelligent artificial hand with force control based on machine vision. Nanotechnology and Precision Engineering. DOI: 10.1063/5.0253551. https://pubs.aip.org/tu/npe/article/9/1/013009/3377418/An-intelligent-artificial-hand-with-force-control.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

Sign in to keep reading

We're committed to providing free access to quality science. By registering and providing insight into your preferences you're joining a community of over 1m science interested individuals and help us to provide you with insightful content whilst keeping our service free.

or

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.