SmartFPS: Neural network based wireless-inertial fusion positioning system

Luchi Hua; Yuan Zhuang; Jun Yang

doi:10.3389/fnbot.2023.1121623

SmartFPS: Neural network based wireless-inertial fusion positioning system

Front Neurorobot. 2023 Feb 10:17:1121623. doi: 10.3389/fnbot.2023.1121623. eCollection 2023.

Authors

Luchi Hua¹, Yuan Zhuang^{2

3

4}, Jun Yang¹

Affiliations

¹ National Application Specific Integrated Circuit Center, Southeast University, Nanjing, China.
² State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China.
³ Hubei Luojia Laboratory, Wuhan, China.
⁴ Wuhan University Shenzhen Research Institute, Shenzhen, China.

Abstract

Current wireless-inertial fusion positioning systems widely adopt empirical propagation models of wireless signals and filtering algorithms such as the Kalman filter or the particle filter. However, empirical models of system and noise usually have lower accuracy in a practical positioning scenario. The biases of predetermined parameters would enlarge the positioning error through layers of systems. Instead of dealing with empirical models, this paper proposes a fusion positioning system based on an end-to-end neural network, along with a transfer learning strategy for improving the performance of neural network models for samples with different distributions. Verified by Bluetooth-inertial positioning in a whole floor scenario, the mean positioning error of the fusion network was 0.506 m. The proposed transfer learning method improved the accuracy of the step length and rotation angle of different pedestrians by 53.3%, the Bluetooth positioning accuracy of various devices by 33.4%, and the average positioning error of the fusion system by 31.6%. The results showed that our proposed methods outperformed filter-based methods in challenging indoor environments.

Keywords: Kalman filter; deep learning; indoor positioning; transfer learning; wireless positioning.

Grants and funding

This research was funded by the National Natural Science Foundation of China, grant numbers 61771135 and 61574033, Excellent Youth Foundation of Hubei Scientific Committee, grant number 2021CFA040, Open Fund of Hubei Luojia Laboratory, grant number 220100037, Knowledge Innovation Program of Wuhan-Shuguang Project, grant number WHKXJSJ013, and GuangDong Basic and Applied Basic Research Foundation, grant number 2021A1515110343.