����Vlog

Most prosthetic hands today still face a basic challenge: no two amputees are alike, yet most devices are built as if they are. This mismatch makes it difficult to achieve natural, intuitive control, often forcing users to constantly adapt to the device rather than the other way around. Even with advances in technology, prosthetic control still relies on weak muscle signals that can change with sweat, skin conditions, or daily movement, creating an unstable link between intention and action that can be frustrating and, in some cases, lead to device abandonment.

����Vlog College of Engineering and Computer Science researchers are addressing this by designing prosthetic systems that adapt to each individual. They begin by 3D scanning a person’s residual limb to create a custom 3D-printed wearable sleeve embedded with soft magnetic sensors that detect subtle muscle changes in real time. Each system is tailored with either 18 or 24 sensors depending on the user’s anatomy and paired with an individualized AI model that learns that person’s unique movement patterns. In testing with 10 study participants, the system showed strong real-time control of multiple hand and wrist gestures and maintained stable performance even under repeated use.

“Prosthetic control is not one-size-fits-all. Every individual brings a distinct movement signature shaped by their anatomy, injury history and how their remaining muscles function,” said Erik Engeberg, senior author. “If we want these systems to truly work in everyday life, they have to be custom fit. By combining 3D-printed wearable sensors with individualized AI models, we’re moving closer to prosthetic systems that can respond naturally and in real time to a person’s intent, rather than forcing users to adapt to the limitations of the device.”

Read the press release.