Research on a gait detection system and recognition algorithm for lower limb exoskeleton robot

The human gait detection system is one of the most important technologies for the intelligentization of the exoskeleton. It has high scientific significance and application prospect in clinical medical diagnosis, evaluation of surgical effects, rehabilitation training, and lower limb exoskeleton design. In this study, a gait detection device is proposed for lower-extremity exoskeleton robots. The device is integrated with smart sensor shoes and has a compact structure and strong practicability. On this basis, the lower limb exoskeleton robot was used as an experimental platform to collect and process human gait data. Furthermore, a new algorithm model of BP neural network based on support vector machines (SVMBP) is proposed. Experimental results show that the gait detection system of SVMBP-based lower limb exoskeleton robot can achieve 6-channel plantar pressure signal acquisition and real-time display. In addition, the average classification and recognition accuracy of the proposed SVMBP model for gait data is 97.4593%, which is 9.3552% higher than the average recognition accuracy of SVM algorithm. Besides, the proposed SVMBP model is less affected by gait and exhibits better algorithm performance. The model is more suitable for gait detection and recognition in wearing exoskeleton robots, and it avoids the shortcomings of SVM in practical applications. The model has the combined advantages of SVM and BP neural network (BPNN) to achieve a good fusion effect.