Task Graph Generation for Heterogeneous UAV Swarms in Partially Observable Adversarial Environments
Wenxin Li, Yongxin Feng · 2026
Read Task Graph Generation for Heterogeneous UAV Swarms in Partially Observable Adversarial Environments by Wenxin Li, Yongxin Feng (2026) 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/PMC13297807.txt.
Description
Drone swarms fighting an unseen adversary must invent their own task lists on the fly, and Wenxin Li with Yongxin Feng offer a method in a 2026 paper. Their system turns local observations, target beliefs, and each aircraft's remaining resources into structured task graphs for mixed fleets.
An offline search program first grades possible futures and teaches a graph attention network what good task structures look like. A manager module then filters tasks, repairs broken dependencies, and checks resources before anything flies. In simulations with heavy observation noise and unfamiliar enemy tactics, the method beat a Graphormer baseline on task-graph utility and edge accuracy, and cut the share of impossible tasks by 35.14%.
Catalog record
| CREATOR | Wenxin Li, Yongxin Feng |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 64490 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |