Research on Gait Recognition of Exoskeleton Robot Based on DTW Algorithm

摘要

The control strategy of exoskeleton robots is currently a hot research topic at home and abroad. How to accurately recognize human gait and improve the real-time performance of the system has always been the main research direction in this field. First, a human gait recognition program is designed, mainly, the human gait information is collected through the sensor, and then the S-G filter is used to preprocess the gait data, then the RLS algorithm is used to predict the gait data, and finally the DTW algorithm is used for Human gait phase recognition. Then, the realization principle of the DTW algorithm is introduced, and corresponding improvement methods are proposed for the shortcomings of the algorithm. Finally, the gait phase recognition test of the human body is carried out on the DTW algorithm before and after the improvement. The experimental results show that compared with the traditional DTW algorithm, the improved DTW algorithm has a certain enhancement in recognition rate and real-time performance.