Research on UWB/IMU location fusion algorithm based on GA-BP neural network

In order to solve the problem of large errors in single positioning technology in complex indoor environments, a positioning fusion method based on GA-BP neural network is proposed. The internal calibration of the IMU is used to reduce or eliminate the coordinate axis deviation and fixed error of the IMU, and the obtained acceleration, angular velocity, attitude Angle information and the PDR positioning mechanism are used to carry out inertial navigation. UWB positioning technology uses an improved TWR ranging algorithm for ranging, and uses the trilateral ranging method to obtain the corresponding coordinates. The BP neural network is used to fuse the data of the two positioning technologies, and the genetic algorithm (GA) is used to optimize the initial weights and thresholds of the BP neural network to improve the performance and prediction accuracy of the network. The experimental results show that the GA-BP neural network integrates the two positioning data and calculates the positioning results. The average positioning error of the GA-BP neural network is 9.6cm, which is about 80% higher than the positioning accuracy of the single positioning method and 43.9% higher than the prediction error of the BP neural network.