一种应用于机器人室内定位的WiFi FLA  

A WiFi FLA for Indoor Robot Positioning

作　　者：叶和敏 彭建盛 YE He-min;PENG Jian-sheng(School of Electronic Engineering,Guangxi Normal University,GuilinGuangxi541004,China;School of Artificial Intelligence and Manufacturing,Hechi University,Yizhou Guangxi546300,China)

机构地区：[1]广西师范大学电子工程学院,广西桂林541004 [2]河池学院人工智能与制造学院,广西宜州546300

出　　处：《计算机仿真》2023年第2期482-485,534,共5页Computer Simulation

基　　金：国家自然科学基金项目(62063006);广西自然科学基金项目(2018GXNSFAA281164)。

摘　　要：针对传统WiFi指纹定位算法定位精度不高,难以满足机器人对室内定位精度要求。提出一种应用于机器人室内定位的WiFi指纹定位算法,通过降低传统算法参考点间距,采用分时段采集方法在每个参考点采集WiFi信号,利用标准化处理方法对WiFi信号进行标准化处理,提高指纹数据的特殊性,运用马氏距离大小作为相似度参考并融合改进的自适应K值WKNN算法,实现指纹匹配准确率的提高。实验结果表明,提出的算法定位精度高于传统算法,定位精度满足机器人室内定位精度的要求。Since the positioning accuracy of traditional WIFI fingerprint positioning algorithm is not high,it is difficult to meet the requirements of indoor positioning accuracy of robots.Therefore,a WIFI fingerprint positioning algorithm applied tofor indoor positioning of robots was proposed.By reducing the reference point spacing of the traditional algorithm,the WiFi signal wais collected at each reference point by the time-divided acquisition method,and the signal iswas dealt with by the standardized processing method to improve the particularity of the fingerprint data.The Mahalanobis distance is was used as the similarity reference and the adaptive K value WKNN algorithm is was integrated,so that the accuracy of fingerprint matching is was improved.Experimental results show that the positioning accuracy of the proposed algorithm is higher than that of the traditional algorithm,and the positioning accuracy meets the requirements of the robot's indoor positioning accuracy.

关 键 词：机器人 室内定位 指纹定位算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]