Object Identification Under Known Dynamics: A PIRNN Approach for UAV Classification
Document Type
Conference Proceeding
Publication Date
1-1-2025
Abstract
This work addresses object identification under known dynamics in unmanned aerial vehicle applications, where learning and classification are combined through a physics-informed residual neural network. The proposed framework leverages physics-informed learning for state mapping and state-derivative prediction, while a softmax layer enables multi-class confidence estimation. Quadcopter, fixed-wing, and helicopter aerial vehicles are considered as case studies. The results demonstrate high classification accuracy with reduced training time, offering a promising solution for system identification problems in domains where the underlying dynamics are well understood.
Publication Source (Journal or Book title)
Proceedings 2025 24th International Conference on Machine Learning and Applications Icmla 2025
First Page
115
Last Page
122
Recommended Citation
Aung, N., Muralles, N., & Stein, A. (2025). Object Identification Under Known Dynamics: A PIRNN Approach for UAV Classification. Proceedings 2025 24th International Conference on Machine Learning and Applications Icmla 2025, 115-122. https://doi.org/10.1109/ICMLA66185.2025.00022