Artificial skin helps robots grasp pencil lead and pull away from needles

Researchers have covered robotic fingers with a new artificial skin that allows the hand to grasp fragile pencil lead and pull away from a needle before it punctures the covering. Both actions depend on more than sensitive sensors. The robot must also receive and interpret their signals quickly enough to respond.

Adding thousands of sensing points makes that harder, because more detailed touch information also means more data to read, transmit and process.

Researchers at Southern University of Science and Technology in China and collaborating institutions tackled that bottleneck with a system inspired by the human sensory nervous system. Described in Nature Machine Intelligence, it reads more than 10,000 sensing elements 100 times a second and processes the information in stages.

Making sense of thousands of signals

Many artificial skins read their sensing points one after another. As the number grows, so do the delays. Nearby sensors can also interfere with one another, blurring the identification of where contact occurred.

The new skin combines flexible electrodes with a soft gel containing electrically charged particles. Pressure changes the electrical response where the gel meets the electrodes, allowing the system to measure touch signals.

To read many sensing points together, the researchers assigned them different signal frequencies within each sensor bundle. Similar to the way individual notes can be picked out of a chord, these signals can be separated even when they arrive together. Frequency identifies the sensing point, while signal strength indicates pressure. The circuitry also limits interference between neighboring sensors.

The system then reduces the amount of data it needs to send onward. An intermediate processing stage, inspired by the spinal cord's role in handling sensory information, compresses the signals before higher-level software interprets them.

The team tested whether useful detail would survive that compression. With the data reduced 268-fold, the system still distinguished among 10 everyday object categories with 98.2% accuracy. The full sequence from sensing through interpretation took about 23 milliseconds.

Knowing when to loosen the grip

Robotic fingers equipped with the skin grasped pencil lead just half a millimeter in diameter. They also handled soft solder wire only 0.2 millimeters thick. When a person made the wire buckle, the fingers adjusted their positions to keep it from falling.

Protecting the skin required another judgment: When was contact becoming dangerous?

The researchers built a calculated "pain" signal from how hard an object pressed, how concentrated the contact was and how abruptly pressure changed across the skin. Sharper objects concentrated pressure into smaller areas, and the signal served as an engineered warning of possible damage.

The robot's response depended on the parameters of the contact. Holding a spiny chestnut prompted the fingers to loosen their grip, but the point of a needle produced highly concentrated pressure that triggered withdrawal. When the protective response was disabled, the fingers continued toward the needle and some sensing areas were damaged.

Making the system compact enough to integrate fully into artificial skin remains a challenge. "The current implementation of the encoding–decoding circuitry is relatively bulky," the researchers write. They propose incorporating it into custom chips, bringing the electronics that interpret touch closer to the flexible covering that detects it.

Written for you by our author Andrew Zinin, edited by Lisa Lock, and fact-checked and reviewed by Robert Egan—this article is the result of careful human work. We rely on readers like you to keep independent science journalism alive. If this reporting matters to you, please consider a donation (especially monthly). You'll get an ad-free account as a thank-you.

Publication details

Zhibin Li et al., Large-scale iontronic skins with neural-hierarchical processing architecture, Nature Machine Intelligence (2026). DOI: 10.1038/s42256-026-01325-6

Who's behind this story?

Andrew Zinin

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Lisa Lock

BA art history, MA material culture. Former museum editor, paramedic, and transplant coordinator. Editing for Science X since 2021. Full profile →

Robert Egan

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

© 2026 Science X Network

Citation: Artificial skin helps robots grasp pencil lead and pull away from needles (2026, October 27) retrieved 27 October 2026 from https://techxplore.com/news/2026-10-artificial-skin-robots-grasp-pencil.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.