Aiming at the problem of establishing mapping model between the received signal strength indication（ RSSI） values and propagation distances in complex indoor environments for radio frequency identification（ RFID）vehicle indoor positioning

an artificial neural network（ ANN） method based on particle swarm optimization（ PSO）is proposed. PSO algorithm is used to optimize weight and threshold parameters of the ANN to avoid the shortcoming of ANN easy to fall into local optimum and establish an accurate classification model for RSSI and tag location. In addition

in order to improve the quality of the training samples and reduce noise interference

Gaussian filtering preprocessing is performed on the experimental data. The experimental result shows that compared with the ANN algorithm

the average error of the proposed PSO-ANN method is reduced by 11. 98 cm

and the performance is more stable.