This paper presents a novel system for autonomous, vision-based drone racing combining learned data abstraction, nonlinear filtering, and time-optimal trajectory planning. The system has successfully been deployed at the first autonomous drone racing world championship: the 2019 AlphaPilot Challenge. Contrary to traditional drone racing systems, which only detect the next gate, our approach makes use of any visible gate and takes advantage of multiple, simultaneous gate detections to compensate for drift in the state estimate and build a global map of the gates. The global map and drift-compensated state estimate allow the drone to navigate through the race course even when the gates are not immediately visible and further enable to plan a near time-optimal path through the race course in real time based on approximate drone dynamics. The proposed system has been demonstrated to successfully guide the drone through tight race courses reaching speeds up to 8m/s and ranked second at the 2019 AlphaPilot Challenge.
@article{arxiv.2005.12813,
title = {AlphaPilot: Autonomous Drone Racing},
author = {Philipp Foehn and Dario Brescianini and Elia Kaufmann and Titus Cieslewski and Mathias Gehrig and Manasi Muglikar and Davide Scaramuzza},
journal= {arXiv preprint arXiv:2005.12813},
year = {2021}
}
Comments
This paper is an extended version of an accepted publication from Robotics: Science and Systems, 2020. This version has been accepted for publication in Autonomous Robots (Springer). Please cite as "AlphaPilot: Autonomous Drone Racing", P. Foehn, Autonomous Robots 2021. Associated video at https://youtu.be/DGjwm5PZQT8