Expertise Affects Drone Racing Performance
This work addresses the lack of understanding of perceptual and motor skills in drone racing, which could inform autonomous flight algorithms, but it is incremental as it primarily documents performance differences.
The study compared professional and beginner drone racing pilots on a real-world track, finding that professionals achieved faster lap times, higher velocities, and more efficient maneuvers, with trajectory analysis showing they chose more optimal racing lines.
First-person view drone racing has become a popular televised sport. However, very little is known about the perceptual and motor skills of professional drone racing pilots. A better understanding of these skills may inform path planning and control algorithms for autonomous multirotor flight. By using a real-world drone racing track and a large-scale position tracking system, we compare the drone racing performance of five professional and five beginner pilots. Results show that professional pilots consistently outperform beginner pilots by achieving faster lap times, higher velocity, and more efficiently executing the challenging maneuvers. Trajectory analysis shows that experienced pilots choose more optimal racing lines than beginner pilots. Our results provide strong evidence for a contribution of expertise to performances in real-world human-piloted drone racing. We discuss the implications of these results for future work on autonomous fast and agile flight. We make our data openly available.