Extra robotic thumb lets wearers complete two-handed tasks with one hand

To complete many everyday tasks and chores, humans typically use both of their hands. For instance, when opening a bottle, they use one hand to hold the bottle and the other to twist its cap. Researchers at the University of California San Diego recently developed EgoThumb, a robotic thumb that could allow people to complete some tasks that generally require both hands using only one.

Their proposed robotic system, introduced in a preprint posted on arXiv, captures images with a small camera, which are then analyzed by an artificial intelligence (AI) algorithm trained to plan the thumb's movements.

"The initial inspiration came from soldering wires," Jiawei Fu, co-first author of the paper, told Tech Xplore.

"Between handling the soldering iron, feeding solder, applying flux and keeping the wires in place, I often felt I needed an extra hand. Even with a 'helping hands' stand, coordinating everything could still be awkward. That made me wonder whether a wearable robotic finger could help hold objects while leaving my own fingers free to work."

Enhancing one-hand manipulation with an extra thumb

Fu and his colleagues set out to develop a compact, wearable robotic system that could serve as an extra thumb to hold objects in place while a wearer's fingers manipulate them. In addition, they wanted the thumb to autonomously determine when to grasp and release objects using images of the wearer's hand and nearby objects, along with information about the thumb's joint positions.

"We wanted that assistance to happen without the user having to explicitly command every movement," explained Fu. "We have not tested soldering itself; this study explores the underlying capability through simpler tasks, such as holding a bottle while unscrewing its cap. Soldering remains one of the practical applications I hope we can work toward."

EgoThumb's robotic thumb has three joints, each driven by a pair of tendons—one for bending and one for straightening. The small motors driving its movements are mounted on a wearer's forearm, keeping their weight off the hand.

The system also includes a small, wide-angle camera, which is mounted close to a wearer's palm. The camera continuously captures images of the user's hand, the robotic thumb and nearby objects.

"We trained an AI model to learn from human demonstrations, an approach called imitation learning," explained Fu. "To collect the training demonstrations, a person controlled the robotic thumb through a foot-operated interface. Once trained, the model predicts the robotic thumb's movements directly from camera images and the thumb's current joint positions, without requiring the user to issue explicit commands."

Fu and his colleagues developed an initial prototype of their robotic thumb. In this prototype, the AI model analyzing camera images and planning future movements runs on an external computer that is connected to the robotic thumb.

The researchers evaluated EgoThumb in laboratory experiments in which three wearers attempted four manipulation tasks. These included picking up a cube, unscrewing a bottle cap, stirring tea and transferring a ball from one location to another. The extra thumb helped wearers complete each type of task using only one hand.

"For example, when a user reaches for a bottle, EgoThumb can automatically grasp and stabilize it, allowing the user's natural fingers to unscrew the cap," said Fu. "When the bottle is put down, EgoThumb releases it."

Fu and his colleagues also assessed the performance of their thumb with different wearers and in different settings. They found that the two new wearers and the initial demonstrator achieved comparable success rates when objects were placed within the same areas the AI algorithm encountered during training.

"The most encouraging finding is that EgoThumb can learn to coordinate with a human hand without requiring the user to explicitly command each grasp," said Fu. "In our initial evaluation, with 10 trials per task per user and objects placed within the same areas used during training, average success across four tasks was 90% for the demonstrator and 92.5% and 87.5% for two new users."

In a separate tea-stirring test, success rates averaged approximately 67% and 73% across three users in two previously unseen settings, respectively. The researchers found that performance declined on some tasks when they expanded the areas where objects were initially found or had to be placed.

A promising system to advance human capabilities

This recent study suggests that an extra robotic thumb could help people perform some tasks one-handed. In the future, the team's EgoThumb could be improved further and tested on a wider range of tasks or scenarios.

"Our findings suggest that vision-based autonomy could make wearable robotic augmentation more natural and intuitive," said Fu. "Rather than requiring people to consciously control an additional finger, the robot can assist based on the context of their actions. We see this as an early step toward wearable robots that complement human dexterity in everyday activities."

The hardware designs and software for EgoThumb are open source and can be accessed by other developers on the project's website. Fu and his colleagues hope that their work will pave the way for more research focusing on intelligent, wearable robotic systems for human augmentation.

Meanwhile, the researchers plan to continue improving EgoThumb. For instance, they would like to make the thumb more compact and comfortable for users by improving how the camera is integrated into the wearable hardware.

"We are also interested in adding tactile sensors to give the robotic thumb a sense of touch, bringing it closer to how a human finger senses and interacts with its surroundings," added Fu. "By combining vision with touch, we hope it could better sense contact with objects and adjust how it holds them, allowing it to assist with a wider range of tasks."

Written for you by our author Ingrid Fadelli, edited by Sadie Harley, 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

Jianyu Hou et al., EgoThumb: A Vision-Driven Supernumerary Robotic Thumb for Autonomous Grasp and Holding Assistance, arXiv (2026). DOI: 10.48550/arxiv.2610.37582

Journal information: arXiv

Who's behind this story?

Ingrid Fadelli

Freelance journalist with BSc Psychology and MA International Journalism. Covers AI, robotics, neuroscience, and astrophysics since 2018. Full profile →

Sadie Harley

BSc Life Sciences & Ecology. Microbiology lab background with pharmaceutical news experience in oil, gas, and renewable industries. 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: Extra robotic thumb lets wearers complete two-handed tasks with one hand (2026, November 10) retrieved 10 November 2026 from https://techxplore.com/news/2026-11-extra-robotic-thumb-wearers-tasks.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.