The purpose of this research is to create an intelligent robotic hand for people who have lost a limb below their elbow. By using artificial intelligence to adaptively grasp different types of objects, this will improve both the accuracy and flexibility of robotic prosthetic control. In addition, the project will integrate mechanical design and artificial intelligence based controls in order to produce a more functional and user-friendly prosthetic solution.
This research develops a low-cost, AI-powered prosthetic system for individuals with transradial amputations. The process begins with a 3D scan of the participant's residual limb to design customized, 3D-printed sockets and robotic hands. The core of the system integrates Artificial Intelligence to classify surface Electromyography (EMG) signals captured from the limb's muscles. This AI-driven pattern recognition allows for adaptive grasping of various objects. The study's primary objective is to compare this AI control system against traditional rule-based EMG programming. Both systems will be evaluated based on their effectiveness, adaptability, and response efficiency while the participant performs real-world grasping activities.
Study Type
INTERVENTIONAL
Allocation
NA
Purpose
DEVICE_FEASIBILITY
Masking
NONE
Enrollment
1
A low-cost, 3D-printed prosthetic hand and customized socket. The device uses AI algorithms to identify objects and adapt grasping patterns, which will be compared against standard rule-based programming.
Al-Nahrain University, College of Engineering
Baghdad, Baghdad Governorate, Iraq
Feasibility and Technical Performance of the AI-driven Prosthetic System.
To evaluate the feasibility of the integrated prosthetic system (3D-printed socket and AI-controlled hand). Feasibility will be assessed by the successful execution of grasp commands using EMG signal classification and the mechanical stability of the 3D-printed components during real-world tasks. This includes the system's ability to maintain functional operation throughout the testing session without hardware or software failure."
Time frame: During the experimental testing sessions (approximately 1 day).
Real-time AI Classification Latency
Measurement of the time delay (in milliseconds) required by the AI algorithm to process raw EMG data and identify the intended grasp pattern
Time frame: During the real-time control evaluation
This platform is for informational purposes only and does not constitute medical advice. Always consult a qualified healthcare professional.