A hierarchical navigation decision-making method for UAV swarms in unknown communication-constrained environments

Huajie Xiong, Baoguo Yu, Jingkui Zhang, He Dong · 2026

Read A hierarchical navigation decision-making method for UAV swarms in unknown communication-constrained environments by Huajie Xiong, Baoguo Yu, Jingkui Zhang, He Dong (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/plos-pone-0339225.txt.

Description

Huajie Xiong and coauthors published a study in PLOS ONE on steering swarms of drones through unknown, obstacle-filled places when the drones cannot talk to each other. Communication limits and small onboard computers make swarm navigation hard, exactly in the disaster settings where swarms would help most. Their framework splits the job in two: an upper planner charting global routes with classic search, and a lower layer where each drone navigates and dodges alone.

The lower layer uses a strengthened feature network trained in two stages, traditional optimization then reinforcement learning, so drones learn robust avoidance. In simulations built on the standard ROS robotics framework, multiple drones navigated complex unknown environments autonomously with no inter-drone communication at all. The authors report clear advantages over existing approaches. Swarms, the design suggests, can stay capable even when radios fail or are jammed, if each drone is smart enough alone.

Catalog record

CREATORHuajie Xiong, Baoguo Yu, Jingkui Zhang, He Dong
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE45819
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0339225

Browse the full library · About the Tower of Babel