NSF Award
2219008
The broader impact/commercial potential of this Partnerships for Innovation - Mid-Career Advancement (PFI (MCA)) project is to increase the capabilities of unmanned aerial vehicles (UAVs) for remote sensing in the Arctic so that vegetation data, which can provide valuable insights into Arctic warming and global climate change, can be collected more readily. The proposed research may result in the development of a flight control method for autonomously flying UAVs over a heterogeneous, vegetation-populated terrain in search of select plant species, and a control method that enables flight in the challenging wind conditions often found in the Arctic. Outcomes from the research seek to benefit the study of the Arctic by increasing opportunities for UAV remote sensor campaigns and their efficient execution. Integrated research, teaching, and outreach activities will be carried out through affiliations with university institutes that foster multidisciplinary collaboration among engineering and other STEM departments, and through collaborations with scholarly organizations that serve currently underrepresented populations. Engagement with industry and federal research agencies will allow technology commercialization for UAV-based Arctic research, agricultural monitoring, and wildfire fighting. <br/><br/>The proposed project seeks to advance UAV capabilities by providing solutions to practical problems that limit their use for remote sensing of the Arctic. Propellers used to control UAV flight are limited in the forces they can produce. If the vehicle’s flight control system requests forces that exceed such limits, undesirable flight performance that jeopardizes the mission may occur. Therefore, deployment of UAVs in the Arctic is currently restricted to infrequent periods when mild winds exist. Likewise, remote sensing by UAV is limited by finite battery life and the need for consistent illumination periods. The goals of the project are to increase periods for remote sensing by providing stable UAV flight during stronger wind conditions and to enable UAVs to collect plant species data autonomously and efficiently. Research objectives include: (a) design of a novel anti-windup compensator that mitigates the effects of propeller saturation enabling UAV operation in challenging wind conditions, (b) development of a reinforcement learning-based autonomous guidance method that searches for specific plant species located in heterogeneous vegetation terrains, and (c) experimental validation of the flight control system with an UAV operating in an Arctic analogous environment.<br/><br/>This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
