Data-Driven Based Cascading Orientation and Translation Estimation for Inertial Navigation
Xiangyu Deng, Shenyue Wang, Chunxiang Shan, Jinjie Lu, Ke Jin, Jijunnan Li, Yandong Guo
Abstract
Recently, data-driven approaches have brought both opportunities and challenges for Inertial Navigation Systems. In this paper, we propose a novel data-driven method which is composed of cascading orientation and translation estimation with IMU-only measurements. For robust orientation estimation, we combine a CNN-based neural network with an EKF to eliminate orientation errors caused by sensor noises. We additionally propose a hybrid CNN-Transformer-based neural network which exploits both spatial and long-term temporal information to regress accurate translations. Specifically, we conduct detailed evaluations on datasets acquired by iPhone and Android devices. The result demonstrates that our method outperforms state-of-the-art methods in both orientation and translation errors.
BibTeX
@inproceedings{iros2023_datadrivenbasedc,
title = {Data-Driven Based Cascading Orientation and Translation Estimation for Inertial Navigation},
author = {Xiangyu Deng and Shenyue Wang and Chunxiang Shan and Jinjie Lu and Ke Jin and Jijunnan Li and Yandong Guo},
booktitle = {IROS 2023},
year = {2023}
}