CTIN: Robust Contextual Transformer Network for Inertial Navigation
Abstract
Recently, data-driven inertial navigation approaches have demonstrated their capability of using well-trained neural networks to obtain accurate position estimates from inertial measurement units (IMU) measurements. In this paper, we propose a novel robust Contextual Transformer-based network for Inertial Navigation~(CTIN) to accurately predict velocity and trajectory. To this end, we first design a ResNet-based encoder enhanced by local and global multi-head self-attention to capture spatial contextual information from IMU measurements. Then we fuse these spatial representations with temporal knowledge by leveraging multi-head attention in the Transformer decoder. Finally, multi-task learning with uncertainty reduction is leveraged to improve learning efficiency and prediction accuracy of velocity and trajectory. Through extensive experiments over a wide range of inertial datasets~(e.g. RIDI, OxIOD, RoNIN, IDOL, and our own), CTIN is very robust and outperforms state-of-the-art models.
Cite
@article{arxiv.2112.02143,
title = {CTIN: Robust Contextual Transformer Network for Inertial Navigation},
author = {Bingbing Rao and Ehsan Kazemi and Yifan Ding and Devu M Shila and Frank M. Tucker and Liqiang Wang},
journal= {arXiv preprint arXiv:2112.02143},
year = {2021}
}
Comments
Accepted as technical research paper in 36th AAAI Conference on Artificial Intelligence, 2022