Prosthetic Hand Achieves Human-Like Dexterity

Engineers at Johns Hopkins University have developed an innovative prosthetic hand that can grasp everyday items, such as water bottles and plush toys, with human-like precision. The hand adjusts its grip to prevent mishandling or damage to the object. The study was published in Science Advances.

Robotic hands have traditionally been too soft or rigid to replicate the human touch. The hybrid design of this new system represents a first in overcoming that limitation. It could improve how robotic arms interact with their environment and offer a promising solution for individuals who have lost their hands.

The goal from the beginning has been to create a prosthetic hand that we model based on the human hand's physical and sensing capabilities—a more natural prosthetic that functions and feels like a lost limb. We want to give people with upper-limb loss the ability to safely and freely interact with their environment, to feel and hold their loved ones without concern of hurting them.

Sriramana Sankar, Ph.D. student and Study Lead, Biomedical Engineering, Johns Hopkins University

The device features a rigid 3D-printed internal skeleton and a multifinger system made of rubber-like polymers. It was developed by the same Neuroengineering and Biomedical Instrumentations Lab that created the first electronic "skin" with a human-like sense of pain in 2018. Unlike conventional touch sensors, its three layers of tactile sensors—modeled after human skin—allow it to grasp and differentiate objects with varying shapes and surface textures.

According to Sankar, machine learning algorithms focus the signals from the artificial touch receptors to simulate a realistic sense of touch. Additionally, the muscles in the forearm control each of its soft, air-filled finger joints.

The sensory information from its fingers is translated into the language of nerves to provide naturalistic sensory feedback through electrical nerve stimulation.

Sriramana Sankar, Ph.D. student and Study Lead, Biomedical Engineering, Johns Hopkins University

The hand successfully recognized and manipulated 15 common objects in the lab, ranging from sturdy items like pineapples and metal water bottles to more delicate objects such as stuffed animals, dish sponges, and cardboard boxes. In the experiments, it outperformed other devices, achieving 99.69 % accuracy and adjusting its grip as needed to prevent damage.

A notable example was when it used just three fingers to gently lift a fragile plastic cup filled with water, without causing any harm to the cup.

“We're combining the strengths of both rigid and soft robotics to mimic the human hand. The human hand isn't completely rigid or purely soft—it's a hybrid system, with bones, soft joints, and tissue working together. That's what we want our prosthetic hand to achieve. This is new territory for robotics and prosthetics, which haven't fully embraced this hybrid technology before. It's being able to give a firm handshake or pick up a soft object without fear of crushing it,” said Sriramana Sankar.

According to Nitish Thakor, a Professor of Biomedical Engineering at Johns Hopkins who led the project, prostheses will need three key components to help amputees regain the sensation of objects while grasping: sensors to detect the surroundings, a system to convert this information into nerve-like signals, and a method to stimulate the nerves, allowing the user to experience the sensation.

Like most hand prostheses, this bioinspired technology enables the hand to function using forearm muscle signals. These signals, which connect the brain and nerves, allow the hand to flex, release, or respond to touch. Thakor explained that the result is a robotic hand that, similar to the nervous system, "knows" what it is touching intuitively.

If you're holding a cup of coffee, how do you know you're about to drop it? Your palm and fingertips send signals to your brain that the cup is slipping. Our system is neurally inspired—it models the hand's touch receptors to produce nervelike messages so the prosthetics' 'brain,' or its computer, understands if something is hot or cold, soft or hard, or slipping from the grip.

Nitish Thakor, Professor, Biomedical Engineering, Johns Hopkins University

Thakor stated that further work is needed to improve the system, though the research marks an early breakthrough for hybrid robotic technology that could transform both robotics and prosthetics. Future improvements may include industrial-grade materials, additional sensors, and stronger grip forces.

“This hybrid dexterity isn't just essential for next-generation prostheses. It's what the robotic hands of the future need because they won't just be handling large, heavy objects. They'll need to work with delicate materials such as glass, fabric, or soft toys. That's why a hybrid robot, designed like the human hand, is so valuable—it combines soft and rigid structures, just like our skin, tissue, and bones,” said Thakor.

The study involved contributions from Jinghua Zhang, Ariel Slepyan, Mark M. Iskarous, Rebecca J. Greene, Rene DeBrabander, and Junjun Chen of Johns Hopkins; Wen-Yu Cheng of Florida Atlantic University; and Arnav Gupta of the University of Illinois Chicago.

The study was supported by the National Science Foundation and the Department of Defense's Orthotics and Prosthetics Outcomes Research Program (W81XWH2010842) under the grant "Neuromorphic Feedback: A Strategy to Enhance Prosthesis Embodiment and Performance."

Video Credit: Johns Hopkins University

Journal Reference:

Sankar, S., et al. (2025). A natural biomimetic prosthetic hand with neuromorphic tactile sensing for precise and compliant grasping. Science Advances. doi.org/10.1126/sciadv.adr9300.