基于多传感器的运动训练辅助机器人主动跟踪算法设计  

Design of Active Tracking Algorithm for Motion Training Assisted Robots Based on Multiple Sensors

作　　者：张馨娇[1] 杨燕[1] ZHANG Xinjiao;YANG Yan(Shangluo University,Shangluo Shaanxi 726000,China)

机构地区：[1]商洛学院,陕西商洛726000

出　　处：《自动化与仪器仪表》2024年第4期171-175,共5页Automation & Instrumentation

基　　金：陕西省体育局《商洛市社区中老年人体育锻炼行为特征及干预措施的实证研究》(2022132)。

摘　　要：针对运动训练辅助机器人对健美操运动员进行检测与跟踪的准确性问题,提出一种基于多传感器的运动训练辅助机器人主动跟踪算法。首先,对主动跟踪算法的总体方案进行设计,提出了基于视觉传感器的机器人主动跟踪方法和基于声纳传感器的机器人主动跟踪方法;然后,采用基于决策层的数据融合方法将两种跟踪方法获取的跟踪方案进行融合,彼此弥补获取最佳的跟踪方案;最后,通过实验测试提出的算法能否实现机器人对健美操运动员的主动跟踪。实验结果表明:设计的基于多传感器的运动训练辅助机器人主动跟踪算法能够让机器人对健美操运动员进行主动跟踪,且整个跟踪过程能够快速检测到目标并朝之靠拢,同时通过调整自身速度安全、平稳地对目标进行跟踪,能够实现辅助运动员进行训练的目的。A multi-sensor based active tracking algorithm for motion training assistance robots is proposed to address the accuracy issue of detecting and tracking aerobics athletes using motion training assistance robots.Firstly,the overall scheme of the active tracking algorithm is designed,and a robot active tracking method based on visual sensors and a robot active tracking method based on sonar sensors are proposed;Then,a decision layer based data fusion method is used to fuse the tracking schemes obtained by the two tracking methods,compensating each other to obtain the best tracking scheme;Finally,through experimental testing,whether the algorithm proposed in this article can achieve active tracking of aerobics athletes by robots.The experimental results show that the multi-sensor based motion training assisted robot active tracking algorithm designed in this article can enable the robot to actively track aerobics athletes,and the entire tracking process can quickly detect and approach the target.At the same time,by adjusting its own speed to safely and smoothly track the target,the goal of assisting athletes in training can be achieved.

关 键 词：运动目标跟踪 视觉传感器 声呐传感器 智能机器人 

分 类 号：TP242[自动化与计算机技术—检测技术与自动化装置]