Stroke patients cannot use their hands as freely as usual. However, recovery after a stroke is a long road for many patients. If artificial intelligence can assist human arm movement, it is believed that the possibility of stroke patients returning to normal hand movement can be significantly increased. In this study, the artificial neuromolecular system (ANM system) developed by our laboratory is used as the core motion control system to learn to control the mechanical arm, produce similar human rehabilitation actions, and assist patients in transiting between different activities. The strength of the ANM system lies in its ability to capture and process spatiotemporal information by exploiting the dynamic information processing inside neurons. Five experiments are conducted in this research: continuous learning, dimensionality reduction, moving problem domains, transfer learning, and fault tolerance. The results show that the ANM system can find out the arm movement trajectory when people perform different rehabilitation actions through the ability of continuous learning and reduce the activation of multiple muscle groups in stroke patients through the learning method of reducing dimensions. Finally, using the ANM system can reduce the learning time and performance required to switch between different actions through transfer learning.
Keywords: computational intelligence; evolutionary learning; rehabilitation; robotic arm; self-organizing learning.