Human motion intention recognition method based on gasbag human-machine interactive force detection and multi-source information fusion

A power-assisted exoskeleton robot can provide its operator a comfortable and natural motion assistance, which requires a perfect human-machine cooperative motion control algorithm according to the operator's intentions. As a bioelectrical signal, surface electromyography (sEMG) has the advantage of real-time for motion control, but its accuracy and reliability are still low due to strong ambiguity and coupling. So interactive force signal is still the most reliable and stable method as the control signal source for human motion intention detection. In this study, a gasbag-based human-machine interaction force signal detection method is proposed, which is combined with bioelectrical signals to identify human motion intentions and take full advantage of the two different control signal sources. A gasbag interactive force detection device is designed to monitor the internal pressure of the gasbag in real time with a pressure sensor, and the signal is converted to an interactive force by a pre-calibrated human- machine interaction force model. The interactive force is fused with the sEMG, the joint angular displacement, and the internal pressure of the pneumatic muscle, then the movement intention of the operator is obtained based on the logistic regression algorithm. Experimental results show that the method for human motion intention recognition has the characters of fast response, accurate recognition and stability.