NSF REU-AUV: Low-Cost Unmanned Surface Vehicle (USV) for Early Detection of Harmful Algal Blooms (HABs)

Abstract: Aquatic ecosystems exist in a fragile balance. The introduction of outside factors, such as invasive species or pollutants, can upset this balance and cause a decline in ecosystem health. Harmful algae blooms, or HABs, can occur when an excess of nutrients are introduced to warm, slow-moving water, often through fertilizer runoff.  Existing methods of testing and monitoring water quality are often slow and time consuming, relying on manual measurements. While mobile solutions exist, they are often expensive and complicated to operate and maintain. Local, state, and federal agencies have expressed interest in finding a more efficient solution to monitor water quality, which would allow them to take measurements in a body of water on large spatial and temporal scales while maintaining low-cost and simple operations.

NSF REU-AUV: Agricultural Weed Mapping Drone 

Abstract: Weeds compete with crops for sunlight, water, nutrients, and growing space, reducing crop yield and increasing production costs. Traditional weed scouting relies on manual field inspections, which are labor-intensive, time-consuming, and often impractical for large agricultural operations. As a result, herbicides are frequently applied uniformly across entire fields, even though weed infestations are typically localized. This approach increases chemical use, raises production costs, and can contribute to environmental impacts and herbicide resistance. Recent advances in unmanned aerial vehicles (UAVs), remote sensing, and artificial intelligence provide new opportunities for precision agriculture. High-resolution aerial imagery collected by drones can be analyzed using computer vision algorithms to identify weeds and generate detailed maps of their locations. 

NSF REU-AUV: Vertical Takeoff and Landing Drone for Wildfire Monitoring and Suppression

Abstract: Wildfires pose a growing threat to ecosystems, infrastructure, and human life, exacerbated by shifting climate patterns and prolonged droughts. Effective wildfire suppression relies heavily on early detection, continuous monitoring, and precise resource allocation. Historically, incident commanders have relied on manned aircraft, satellite imagery, and ground crews to gather intelligence. However, satellite data often suffers from latency and resolution limits, while manned aircraft are expensive, limited by severe smoke or nighttime conditions, and put pilots at extreme risk. In recent years, Unmanned Aerial Vehicles (UAVs) have emerged as a safer, cost-effective alternative. Standard multirotor drones offer excellent maneuverability for close-up inspections but lack the battery life and range required to monitor large, fast-moving fires. Conversely, fixed-wing drones provide the necessary range but require open space or specialized equipment for launch and landing, ideal for densely forested areas. To overcome these limitations, this project focuses on VTOL technology.

NSF REU-AUV: Development of a Multi-Agent UAV-UGV System for Autonomous Operations in Hazardous Environments

Abstract: As global communities face an increase in frequency and intensity of natural and anthropogenic disasters, the demand of relief and surveillance systems reach an all time high. This poster presents a Multi-Agent System (MAS) comprising of an Unmanned Aerial Vehicle (UAV) and an Unmanned Ground Vehicle (UGV) framework that offers increased situational awareness in areas affected by disasters, hazardous environments, high-risk zones. By utilizing the aerial-robustness of the UAV and the ground-mobility of the UGV, the system can access areas inaccessible to traditional search-and-rescue teams. UAVs can quickly assess affected areas from the air, while UGVs can perform closer inspections on the ground. In this project, our team is developing a heterogeneous UAV–UGV system to make search-and-rescue operations safer and more reliable in hazardous environments.