CTIN: Robust Contextual Transformer Network for Inertial Navigation
This work addresses inertial navigation for applications like robotics or wearables, but it appears incremental as it builds on existing data-driven approaches with architectural improvements.
The paper tackled the problem of accurate position estimation from inertial measurement units (IMU) by proposing a robust Contextual Transformer-based network (CTIN) that predicts velocity and trajectory, and it outperformed state-of-the-art models across multiple datasets.
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.