AI-based Semiautonomous Control Strategy for upper-limb prostheses

Artificial Intelligence-based Semiautonomous control strategies (AI-based SCS) could significantly improve the reliability and naturalness of prosthetic hand control. The integration of a computer vision system (CVS) and the user motion intention allows the prosthetic hand to autonomously recognize the object to be grasped and to select the appropriate hand posture, with the user in charge of initiating the execution of the grasp. In this work, an AI-based SCS integrating EMG signals with a CVS is presented. The control strategy was assessed both in laboratory settings and in more complex real life scenarios. The results show strong performance of the proposed SCS with an Accuracy in Object and Grasp Classification above 97%, a Mean Time of Execution of 0.483s, and a Mean Angular Error and Estimation Stability in wrist orientation of 16.26 ± 8.62° and 0.2, respectively. The control strategy effectively managed also complex situations, achieving a 100% Success Rate in the conducted tests.