Collaborative Control of Multiple UAVs for Wildfire Tracking and Monitoring. According to the U.S. Forest Service, an annual average of 70,000 wildfires burn approximately 7 million acres of land and destroy more than 2,600 structures. Wildland firefighting is dangerous and a lack of information is one of the main causes of accidents. Unmanned aerial vehicles (UAVs) provide situational awareness of wildfire scenes because they can augment hazardous fire-tracking activities and significantly save operational costs. The UNR team, lead by Dr. Hung La, developed a distributed control framework for a team of UAVs to monitor wildfire in open space and precisely track its development. The UAVs are designed for flexible deployment and to effectively avoid in-flight collisions and cooperate well with other UAVs. Each UAV self-learns and adjusts its altitude to provide optimal coverage of an unknown field. The proposed controller was tested in simulation (Figures 1 & 2) and on an AR2 drone using a motion capture system in the Advanced Robotics and Automation (ARA) Lab.
Monopolistic Behaviors in Unmanned Airspace. During my graduate studies at the University of Nevada, Reno (UNR), under Dr. Yliniemi, I worked on a model enhancement to include more realistic unmanned airspace flight patterns for NASA’s Unmanned Traffic Management (UTM) system. The current methods for modeling multiple subsystems of autonomous Unmanned Aerial Vehicles (UAVs) do not account for competitive markets. By making modifications to an existing multi-UAV model, we investigated different behavioral interactions between the multiple subsystems and showed how competitive behaviors affect each subsystem.