Abstract: Lower limb exoskeleton (LLEXO) robot is a kind of intelligent wearable device used to assist human lower extremity to achieve power movement. And human gait recognition is one of the most important technologies to realize the intelligence of exoskeleton robot. A gait detection (HG) system was proposed for lower extremity exoskeleton robots, which realized the integration of the device into smart sensor shoes, and it was compact and practical. On this basis, the LLEXO experimental prototype was used to was used to conduct human gait data collection experiments. Meanwhile, the SVMBP motion recognition algorithm was proposed, which was based on the integration of the advantages of the support vector machine (SVM) and back propagation neural network (BPNN) algorithm models. The experimental results show that the SVMBP-based LLEXO HG system c an complete 6 channel plantar pressure signal acquisition and real-time display. And the proposed SVMBP model had an average classification and recognition accuracy of 99.39% for gait data, the average recognition accuracy was higher than the single SVM and BPNN algorithm, and the recognition of each phase during walking was more stable, which enhanced the reliability of the algorithm and improves the recognition accuracy of the algorithm.

Key words: smart sensor shoes, gait detection and recognition, support vector machine, neural network, SVMBP model, lower limb exoskeleton