A Hybrid CNN-LSTM Network With Attention Mechanism For Myoelectric Control In Upper Limb Exoskeletons

This paper introduces a novel attention-based sequence-to-sequence network for predicting upper-limb exoskeleton joint angles, enhancing the control of assistive technologies for individuals with upper limb impairments. By integrating EMG and IMU signals, our model facilitates real-time decoding of user intentions, generating precise movement trajectories for a 3-DoF cable-driven upper-limb exoskeleton. The implementation of an attention mechanism within an encoder-decoder architecture allows for the dynamic prioritization of the most pertinent EMG features and historical angular positions, significantly improving prediction accuracy and system responsiveness. This approach not only offers a tailored response to varying sequence lengths and compensates for sensor unreliability but also introduces a level of personalization and adaptability previously unattainable in robotic rehabilitation and assistive devices. Through this model, we demonstrate a more effective, user-specific method of enhancing motor function recovery and facilitating daily activities, setting a new standard for assistive exoskeleton technology.