Development of a Fixed-Wing UAV Testbed for In-Flight Data Collection from an Event-Based Camera
Paul Coen, Bart Cox, Or D. Dantsker
- Year
- 2026
- Citations
- 2
Abstract
Event-based cameras represent a novel sensing modality offering high temporal resolution, low latency, and increased dynamic range compared to traditional frame-based systems. Their integration in aerial robotics has been largely restricted to multi-rotor platforms due to the complexity involved in fixed-wing development. This paper addresses the gap in aviation-specific research by presenting the development of the first fixed-wing Unmanned Aerial Vehicle (UAV) test bed designed for event-based data collection to compare against a frame-based method. The experimental platform utilizes a 26% scale Cub Crafters CC11-100 Sport Cub S2, outfitted with a custom data acquisition payload containing a Triton2 EVS 0.9MP event camera, an HD global shutter RGB frame camera, and an Xsens IMU/GNSS unit. The system design prioritized Size, Weight, and Power (SWaP) requirements to ensure endurance and flight stability while maintaining the computational capacity necessary for high-bandwidth data recording of all sensors. Flight tests validated the system's operational capabilities and informed new requirements for future modifications. The flights demonstrated the event camera's superior performance in high-dynamic-range scenarios when flying towards the sun. Results indicate that while traditional frame cameras suffer from overexposure when flying into the sun, event sensors successfully retain feature visibility and data integrity. This work constitutes the first reported application of an event camera on a fixed-wing UAV, establishing a foundational framework for future research into aviation-specific perception and navigation tasks.
Keywords
Related papers
Artificial intelligence: a modern approach
1995
Are we ready for autonomous driving? The KITTI vision benchmark suite
Andreas Geiger, P Lenz, R. Urtasun
2012
Self-Organizing Maps
Teuvo Kohonen
1995
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
Martı́n Abadi, Ashish Agarwal, Paul Barham +17 more
2016