Researchers Develop Improved, Intuitive Bionic Hand That Incorporates Shared Human and Machine Control

Researchers supported in part by NIH have developed a bionic hand that uses shared human and machine control, resulting in greater grip security and precision and less cognitive burden than current products. Their findings were recently published in Nature Communications.

Currently available bionic hands can replicate many movements of the human hand, but controlling bionic hands is not an easy or intuitive task for individuals with hand amputation. Many users of these prostheses stop using them citing poor control and cognitive burden as primary reasons. Biological hands can transition between numerous grip patterns and intensities thanks to an intricate neural encoding of hand control in terms of joint position. Ideally, users of a bionic hand could similarly control the position of their fingers and the force of their grasps in relation to what they want their hand to do.

The research team wanted to see if they could get closer to achieving this goal by developing a bionic hand that blends both human and machine control for a particular grasp. They incorporated multimodal fingertip sensors capable of detecting both proximity and pressure into a commercial prosthetic hand and established a new autonomous closed-loop machine controller for the prosthesis to enhance grasping precision and stability. They then added a new shared control framework that combines both human and machine intent. Artificial intelligence moved each finger to the point of contact while the user controlled the grasp with surface electromyography, keeping the user in control of the grasp while receiving subtle assistance from the machine.

They found that this shared control framework allows the machine to assist the user with a variety of real-world tasks and grasps that require unique finger positions and force. In a series of experiments with both participants with intact limbs and participants with upper limb amputations, they found that this shared control led to greater grip precision and improved grip security while reducing cognitive burden.

According to the researchers, these findings serve as proof-of-concept that this kind of shared user and machine control can increase the benefits of using a prosthetic hand and represent an important step toward the development of more dexterous and intuitive bionic arms.

Reference:

Trout, MA et al. Shared human-machine control of an intelligent bionic hand improves grasping and decreases cognitive burden for transradial amputees. Published December 9, 2025 in Nature Communications. https://doi.org/10.1038/s41467-025-65965-9