An Unsupervised Situation Awareness Framework for UAV Sensor Data Fusion Enabled by a Stabilized Deep Variational Autoencoder
Anxin Guo, Zhenxing Zhang, Rennong Yang, Ying Zhang, Liping Hu, Leyan Li · 2025
Read An Unsupervised Situation Awareness Framework for UAV Sensor Data Fusion Enabled by a Stabilized Deep Variational Autoencoder by Anxin Guo, Zhenxing Zhang, Rennong Yang, Ying Zhang, Liping Hu, Leyan Li (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12787978.txt.
Description
Anxin Guo and co-authors build, in a 2025 paper, an unsupervised framework that helps drones make sense of their own sensor streams. Situation awareness depends on fusing GPS, motion, and radar feeds in real time. Standard deep generative models wobble badly when trained on such flight data.
Their model steadies training with weighted uncertainty and a mixture output that handles many flight styles. In tests, ordinary versions of the model often failed to converge on this data. The stabilized version extracted usable features from nonlinear time series. No labeled examples guide the learning, which suits raw flight logs. Reliable self-monitoring is a step toward drones that can judge their own state.
Catalog record
| CREATOR | Anxin Guo, Zhenxing Zhang, Rennong Yang, Ying Zhang, Liping Hu, Leyan Li |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 56 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |