Investigation of Future Voluntary Movement Prediction for Pathological Tremor-Alleviating Exoskeletons

Abstract

Pathological tremor, a common neurological disorder, significantly impacts patients' daily quality of life and causes difficulties with performing simple daily tasks. Those tremors usually interfere with the patient's fine motor control and may also cause psychological anxiety and social barriers. Traditional treatments, such as medication and physical therapy, can alleviate symptoms to a certain extent; however, their effects are limited, and they may also have side effects. Therefore, rehabilitation exoskeletons have emerged as an assistive technology and have become an essential supplement to traditional treatments. Then, performance optimization is particularly critical to fully realizing the potential of exoskeletons. The ideal tremor suppressor exoskeleton not only needs to suppress tremors effectively but also must be able to distinguish and predict the patient's autonomous movements. These requirements can ensure that the exoskeleton minimizes the influence of involuntary tremors while facilitating the patient's voluntary movements, enabling patients to experience a smooth and natural operational experience similar to that of normal movement. The wrist is a critical component of human operational capability, with its flexibility and precision playing an important role in daily activities. However, it is also a common site for pathological tremors. Our research laboratory has developed a wearable exoskeleton termed TAWE to address this issue. TAWE uses a 6-degree-of-freedom (DOF) rigid link mechanism, which can precisely replicate the natural range of motion of the wrist while simultaneously providing real-time suppression of pathological tremors without compromising the user's freedom of movement. Therefore, we developed a deep learning model based on a convolutional neural network (CNN) and self-attention mechanism to accurately extract and predict patients' voluntary movement intentions from tremor-affected motion data. This model enables real-time motion planning for the exoskeleton, achieving both tremor suppression and zero-latency performance. This model is capable of directly predicting voluntary movement trajectories approximately 100 milliseconds in advance from real-time input data. Finally, we comprehensively evaluated the model's performance and its real-time capabilities when integrated into the exoskeleton system through simulation experiments. Overall, the CNN-Self-Attention-based model has strong performance and can predict autonomous motion trajectories for the next 100 milliseconds in real-time, regardless of whether the input data included tremor interference. However, the results also revealed certain model limitations under extreme conditions, such as high-frequency and large-amplitude tremors. In these cases, the output trajectory remained insufficiently smooth even after processing, resulting in slight stuttering during exoskeleton movement. These problems need further research and improvement.