Research On Indoor Navigation And Positioning Algorithm Based On RSSI Ranging

With the rapid development of network technology and intelligent terminal,people’s demand for location service is increasing.According to statistics,the number of mobile phone users has exceeded 1.57 billion.At present,the global navigation and positioning system can provide accurate outdoor navigation location services.However,due to the complex indoor environment,serious signal interference,and with the gradual increase of large buildings,how to improve the indoor positioning accuracy to meet the needs of people’s lives has become the current research hotspot.Considering the cost and accuracy of indoor positioning,this paper selects the indoor positioning algorithm based on RSSI(Received Signal Strength Indictor)ranging to study.The main work is as follows:(1)The existing location algorithms based on ranging and non ranging are synthetically analyzed,and the applicability of various algorithms is discussed in depth.At the same time,time of arrival(TOA),time difference of arrival(TDOA),angle of arrival(AOA),received signal strength(RSSI)are discussed.The advantages and disadvantages of four ranging methods are analyzed.(2)To solve the problem that the existing path loss model can not well represent the relationship between distance and signal strength,this paper introduces the path loss model based on GA-BP neural network training.The model is based on the path loss model trained by BP neural network.The initial weight and threshold value of BP neural network are improved by using genetic algorithm,which improves the defect that BP neural network is easy to fall into local extreme value,so as to improve the ranging accuracy(3)Aiming at the problem that the existing centroid algorithm based on signal strength can not meet the needs of high-precision indoor positioning in specific scenes,an improved weighted centroid positioning algorithm is proposed.In this algorithm,the distance between four known anchor nodes and the point to be measured is obtained by RSSI ranging.Draw an arc with the coordinates of the corresponding anchor node as the center and the distance value as the radius,and the quadrilateral area intersected by four arcs is obtained.Any three vertices can form a triangle,then the sum of the reciprocal squares of the distance is used as the weight to calculate the coordinates of the four triangles,and then the coordinates of the four triangles are used as the initial values.The sum of signal strength is used as the weight to calculate the coordinates of the point to be measured.(4)Through the MATLAB simulation and the actual data experiment,it shown that the distance measurement accuracy of the path loss model trained by GA-BP neural network was higher than that of the path loss model trained by BP neural network;the positioning accuracy of the improved weighted centroid algorithm was better than that of the existing weighted centroid algorithm;Finally,the feasibility of this method is verified by comprehensive experiments..