Design and Validation of a Novel Human–Machine Interface System Based on Multisource Data Fusion

Conventional human-machine interface (HMI) systems generally take surface electromyography (sEMG) as the only signal source, which often faces the problem of multichannel crosstalk. To enhance HMI performance, this study introduces a novel three-degree-of-freedom (3-DOF) HMI system for surgical robot control, which integrates sEMG signals and inertial measurement unit (IMU) signals. A cost-effective wearable HMI hardware system is designed to address the high price and poor portability of existing commercial equipment, which also has a higher signal-to-noise ratio (SNR) of 35.9 dB. Based on the proposed simultaneous and proportional control (SPC) strategy, ten subjects were recruited to conduct an online experiment involving four upper limb postures to assess the real-time performance of the HMI system. In addition, six able-bodied participants participated in a validation experiment to statistically verify and rigorously evaluate the implemented HMI system. The experimental results demonstrate that our HMI system can accurately decode the angles of the wrist and metacarpophalangeal (MCP) joints in both single-DOF and 3-DOF movements, achieving stable control and robust online performance. Furthermore, the proposed HMI system was applied to a flexible endoscopic robot to realize remote SPC, and the results indicate that it can perform well in the practical application. The current study proves the feasibility and practicability of multisource data fusion for HMI, providing a new direction.