Towards Biosignals-Free Autonomous Prosthetic Hand Control via Imitation Learning

Limb loss affects millions globally, impairing physical function and reducing quality of life. Both traditional surface electromyographic (sEMG) and semi-autonomous methods require users to generate myoelectric signals for each control, imposing physically and mentally taxing demands. This study aims to develop a fully autonomous control system that enables a prosthetic hand to automatically grasp and release objects of any shape using only a camera attached to the wrist. By placing the hand near an object, the system will automatically execute grasping actions with a proper grip force in response to the hand’s movements and the environment. To release the object being grasped, just naturally place the object close to the table and the system will automatically open the hand. Such a system would provide persons with limb loss with a very easy-to-use prosthetic control interface and greatly reduce mental effort while using. To achieve this goal, we developed a teleoperation system to collect human demonstration data for training the prosthetic hand control model using imitation learning, which mimics the prosthetic hand actions from human. Through training the model using only a few objects data from one single participant, we have shown that the imitation learning algorithm can infer grasping and releasing with high accuracy, generalizing to more individuals and unseen objects with a variation of weights.

Supplementary video

A longer unedited demo

What can we do between grasping and releasing? (Using the same trained model as above)

Interview By CBC

Interview by tehxplore: https://techxplore.com/news/2025-06-reliably-prosthetic-movements-biological.html