Artificial intelligent based control strategy for reach and grasp of multi-objects using brain-controlled robotic arm...

Area of Science:

• Biomedical Engineering
• Neuroscience
• Artificial Intelligence

Background:

• Brain-controlled robotic arm systems offer communication and control for individuals with severe motor impairments.
• Conditions like spinal cord injury, stroke, and neurological diseases limit mobility and daily activity.
• Existing systems aim to restore function through advanced assistive technologies.

Purpose of the Study:

• To propose an artificial intelligence (AI)-based control strategy for a brain-controlled robotic arm system.
• To enable users to control the robotic arm for reaching and grasping multiple objects using brain signals.
• To enhance the capabilities of assistive devices for individuals with paralysis.

Main Methods:

• Utilizing an electroencephalogram (EEG) cap to capture brain activity.
• Implementing an AI algorithm to translate EEG signals into robotic arm commands.
• Designing an improved ResNet pre-trained architecture for deep feature extraction from EEG signals.
• Employing a threefold process: feature extraction, feature optimization, and control strategy classification.

Main Results:

• The proposed AI strategy facilitates control over a robotic arm's reach and grasp functions.
• Deep feature extraction using an improved ResNet architecture enhances EEG signal processing.
• The system translates brain signals into precise commands for complex object manipulation tasks.

Conclusions:

• AI-powered brain-controlled robotic arms can significantly improve the quality of life for individuals with motor disabilities.
• This technology empowers users to perform daily activities independently.
• The developed control strategy shows promise for advanced human-robot interaction in assistive applications.