Date of Award


Degree Type


Degree Name

Doctor of Philosophy (PhD)


Computer Science

First Advisor

Dr. Xiaolin Hu


Unmanned Aircraft Systems (UASs) offer many benefits in wildfire monitoring when compared to traditional wildfire monitoring technologies. When planning the path of an UAS for wildfire monitoring, it is important to consider the uneven propagation nature of the wildfire because different parts of the fire boundary demand different levels of monitoring attention (importance) based on the propagation speed. In addition, many of the existing works adopt a centralized approach for the path planning of the UASs. However, the use of centralized approaches is often limited in terms of applicability and adaptability. This work focuses on developing decentralized UAS path planning algorithms to autonomously monitor a spreading wildfire considering uneven importance. The algorithms allow the UASs to focus on the most active regions of a wildfire while still covering the entire fire perimeter.

When monitoring a relatively smaller and spatially static fire, a single UAS might be adequate for the task. However, when monitoring a larger wildfire that is evolving dynamically in space and time, efficient and optimized use of multiple UASs is required. Based on this need, we also focus on decentralized and importance-based multi-UAS path planning for wildfire monitoring. The design, implementation, analysis, and simulation results have been discussed in details for both single-UAS and multi-UAS path planning algorithms. Experiment results show the effectiveness and robustness of the proposed algorithms for dynamic wildfire monitoring.


File Upload Confirmation