基于时间序列分析的可穿戴助力机器人传感器信号预测的研究

下肢可穿戴助力机器人是一种自主控制的机器人.它要求各个关节的电机根据感知系统获取的力信息和位置信息做出快速反应.为了提高下肢可穿戴助力机器人的动态响应频率,本文提出了一种新颖的基于时间序列分析的感知系统信号在线预测算法,该算法在保证系统实时性的前提下,提高了感知系统的动态响应频率.在文章的最后,对信号预测算法进行了相应的实验,实验结果表明了该算法的准确性和有效性.

Study on Sensing Information Forecasting of Wearable Power Asist Walking Legs Based on Time Series Analysis

The Wearable Power Assist Walking Legs (PAWL) is an autonomous exoskeleton robot, which requires the actuators can response rapidly according to the force information and the angle information from the sensing system. In order to improve the dynamic response of the whole system, we propose a novel forecasting algorithm based on time series analysis. Because of the requirement of the real-time, the forecasting algorithm is designed for utilizing on-line. In the end, some correlative experiments have been made and the results illustrate the validity and effectiveness of the algorithm.