融合AOA与射频RSS的KNN指纹室内定位算法

KNN Fingerprint Indoor Location Algorithm Combining AOA and RF RSS

为了解决基于蓝牙射频RSS的室内定位算法精度低、实时性差等问题,提出一种融合到达角(Angle of Arrival,AOA)与射频RSS的K近邻指纹定位算法,通过采集NRF51822传感器的射频RSS聚类信号形成定位指纹库,采用KNN欧式最优算法与指纹库进行匹配得出近似坐标位置,设计一款小型PCB八木天线模拟定位基站,补偿射频RSS随距离、遮挡等造成的信号接收强度指示(Received Signal Strength Indicator,RSSI)跳变、衰减,通过信标与定位节点的AOA到达角与最优指纹数据的权值归一化换算,得出最终定位坐标。实验结果表明,该算法具有定位精度高、实时性好等优点,具有较高的推广价值。

In order to solve the problems of low accuracy and poor real-time performance of indoor positioning algorithm based on Bluetooth radio frequency RSS, a K-nearest neighbor fingerprint positioning algorithm integrating Angle of Arrival (AOA) and radio frequency RSS is proposed. By collecting the RF RSS clustering signal of NRF51822 sensor to form a positioning fingerprint library, KNN European optimal algorithm is used to match the fingerprint library to obtain the approximate coordinate position. A small PCB Yagi antenna simulation positioning base station is designed to compensate the RSSI jump and attenuation caused by distance and occlusion of RF RSS. The final positioning coordinates are obtained by the normalizing the AOA of beacon and positioning node and the weight of optimal fingerprint data. The experimental results show that the algorithm has the advantages of high positioning accuracy, good real-time performance, and the algorithm has high promotion value.