Research Article
LS-SVM/Federated EKF Based on the Distributed INS/UWB Integrated 2D Localization
@INPROCEEDINGS{10.1007/978-3-030-82562-1_49, author={Fukun Li and Shuhui Bi and Meng Wang and Liyao Ma and Bo Zhang}, title={LS-SVM/Federated EKF Based on the Distributed INS/UWB Integrated 2D Localization}, proceedings={Multimedia Technology and Enhanced Learning. Third EAI International Conference, ICMTEL 2021, Virtual Event, April 8--9, 2021, Proceedings, Part I}, proceedings_a={ICMTEL}, year={2021}, month={7}, keywords={INS/UWB-integrated positioning Seamless navigation LS-SVM Federated EKF}, doi={10.1007/978-3-030-82562-1_49} }- Fukun Li
Shuhui Bi
Meng Wang
Liyao Ma
Bo Zhang
Year: 2021
LS-SVM/Federated EKF Based on the Distributed INS/UWB Integrated 2D Localization
ICMTEL
Springer
DOI: 10.1007/978-3-030-82562-1_49
Abstract
In this paper, a novel distributed integrated 2D localization scheme for fusing the fusing the ultra wide band (UWB)- and inertial navigation system (INS)-derived ranges using least squares-support vector machines (LS-SVM)/federated extended Kalman filter (FEKF) integrated approach is presented. In the proposed scheme, the local filter is capable of fusing UWB- and INS-derived distances, and then, the main filter is employed to fuse the local data fusion filter’s outputs and compensate the INS position error. Moreover, for overcoming the outage of the UWB, the LS-SVM is used to assist the FEKF, which can compensate the missing UWB measurement. The test demonstrates that the proposed LS-SVM/FEKF can effectively improve the position accuracy compared with the traditional FEKF.
