DiffusionIMU: Diffusion-Based Inertial Navigation with Iterative Motion Refinement

Teng, Xiaoqiang; Li, Chenyang; Xu, Shibiao; Hao, Zhihao; Guo, Deke; Li, Jingyuan; Li, Haisheng; Meng, Weiliang; Zhang, Xiaopeng

doi:10.24963/ijcai.2025/977

DiffusionIMU: Diffusion-Based Inertial Navigation with Iterative Motion Refinement

Xiaoqiang Teng, Chenyang Li, Shibiao Xu, Zhihao Hao, Deke Guo, Jingyuan Li, Haisheng Li, Weiliang Meng, Xiaopeng Zhang

Download BibTeX Cite

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence. Main Track. Pages 8787-8795.

https://doi.org/10.24963/ijcai.2025/977

Keywords

Robotics: ROB: Applications
Robotics: ROB: Localization, mapping, state estimation
Computer Vision: CV: Motion and tracking
Robotics: ROB: Learning in robotics

Abstract

Inertial navigation enables self-contained localization using only Inertial Measurement Units (IMUs), making it widely applicable in various domains such as navigation, augmented reality, and robotics. However, existing methods suffer from drift accumulation due to the sensor noise and difficulty capturing long-range temporal dependencies, limiting their robustness and accuracy. To address these challenges, we propose DiffusionIMU, a novel diffusion-based framework for inertial navigation. DiffusionIMU enhances direct velocity regression from IMU data through an iterative generative denoising process, progressively refining motion state estimation. It integrates the noise-adaptive feature modulation for sensor variability handling, the feature alignment mechanism for representation consistency, and the diffusion-based temporal modeling to decrease accumulated drift. Experiments show that DiffusionIMU consistently outperforms existing methods, demonstrating superior generalization to unseen users while alleviating the impact of the sensor noise.

Xiaoqiang Teng, Chenyang Li, Shibiao Xu, Zhihao Hao, Deke Guo, Jingyuan Li, Haisheng Li, Weiliang Meng, and Xiaopeng Zhang. 2025. DiffusionIMU: Diffusion-Based Inertial Navigation with Iterative Motion Refinement. In Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25. IJCAI, 8787–8795. https://doi.org/10.24963/ijcai.2025/977

@inproceedings{ijcai2025p977,
  title     = {DiffusionIMU: Diffusion-Based Inertial Navigation with Iterative Motion Refinement},
  author    = {Teng, Xiaoqiang and Li, Chenyang and Xu, Shibiao and Hao, Zhihao and Guo, Deke and Li, Jingyuan and Li, Haisheng and Meng, Weiliang and Zhang, Xiaopeng},
  booktitle = {Proceedings of the Thirty-Fourth International Joint Conference on
               Artificial Intelligence, {IJCAI-25}},
  publisher = {International Joint Conferences on Artificial Intelligence Organization},
  editor    = {James Kwok},
  pages     = {8787--8795},
  year      = {2025},
  month     = {8},
  note      = {Main Track},
  doi       = {10.24963/ijcai.2025/977},
  url       = {https://doi.org/10.24963/ijcai.2025/977},
}

TY  - CPAPER
TI  - DiffusionIMU: Diffusion-Based Inertial Navigation with Iterative Motion Refinement
AU  - Teng, Xiaoqiang
AU  - Li, Chenyang
AU  - Xu, Shibiao
AU  - Hao, Zhihao
AU  - Guo, Deke
AU  - Li, Jingyuan
AU  - Li, Haisheng
AU  - Meng, Weiliang
AU  - Zhang, Xiaopeng
T2  - Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, IJCAI-25
PB  - International Joint Conferences on Artificial Intelligence Organization
PY  - 2025
SP  - 8787
EP  - 8795
DO  - 10.24963/ijcai.2025/977
UR  - https://doi.org/10.24963/ijcai.2025/977
ER  -