Code for the paper:

Hybrid Models for Situational Awareness of an Aerial Vehicle from Multimodal Sensing
O. Tanay Topac, Sung Yeon Sara Ha, Xiyuan Chen, Lawren Gamble, Daniel Inman and Fu-Kuo Chang
AIAA Journal (2022)
https://doi.org/10.2514/1.J061926

Aircraft have long been utilizing reliable but heavy and limited capability sensors to identify their flight state (speed, flight angle, etc.). We present an integrated system that includes a low-profile network of sensors embedded into the aerodynamic surface of an aircraft wing and a set of specialized AI models fed by the data obtained from these sensors. We demonstrate that our system can predict the most commonly sought-after flight data as well as safety-critical conditions with very high accuracy, paving the way for a novel aircraft instrumentation method.

This repository includes code for real-time data acquisition, training, inference, and visualization, as described in the paper.

Accompanying data that includes the training dataset and one dynamic test case can be accessed at the following link: https://drive.google.com/drive/folders/12UpNMcbqcyvTlLvmXzf0lrvLzKwJ6QKE?usp=sharing

Feel free to reach out for comments/suggestions, if you face any issues running the program, or if you'd like access to other dynamic test cases.

Please cite our work as:

@article{topacHybridModelsSituational2022,
  title = {Hybrid Models for Situational Awareness of an Aerial Vehicle from Multimodal Sensing},
  author = {Topac, O. Tanay and Sara Ha, Sung Yeon and Chen, Xiyuan and Gamble, Lawren and Inman, Daniel and Chang, Fu-Kuo},
  year = {2022},
  month = Oct,
  journal = {AIAA Journal},
  pages = {1-10},
  doi = {10.2514/1.J061926},
}