当前位置: X-MOL 学术arXiv.cs.HC › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Expertise Affects Drone Racing Performance
arXiv - CS - Human-Computer Interaction Pub Date : 2021-09-15 , DOI: arxiv-2109.07307
Christian Pfeiffer, Davide Scaramuzza

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.

中文翻译:

专业知识影响无人机赛车性能

第一人称视角无人机赛车已成为一项流行的电视运动。然而,对于专业无人机赛车飞行员的感知和运动技能知之甚少。更好地理解这些技能可以为自主多旋翼飞行的路径规划和控制算法提供信息。通过使用真实世界的无人机赛道和大型位置跟踪系统,我们比较了五名专业飞行员和五名初学者的无人机赛车性能。结果表明,专业飞行员通过实现更快的单圈时间、更高的速度和更有效地执行具有挑战性的操作,始终优于初学者。轨迹分析表明,有经验的飞行员比初学者选择更多的最佳赛车路线。我们的结果提供了强有力的证据,证明专业知识对现实世界人类驾驶无人机比赛中的表现的贡献。我们讨论了这些结果对未来自主快速和敏捷飞行工作的影响。我们公开提供我们的数据。
更新日期:2021-09-16
down
wechat
bug