Multi sensor indoor location method based on Neural Network

Abstract:
Aiming at the problem that the positioning of indoor mobile machines cannot be solved by a single sensor. A positioning system based on multi-sensor data fusion is designed. Firstly, the system constructs an RNN network, which uses the RSSI characteristics of Wi-Fi signal as the input. After training, the network output’s location information; Then the positioning results are fused with the positioning results of low-cost MEMS inertial measurement elements to improve the positioning accuracy of the system. Finally, the experimental results show that the method is effective.