Abstract
We present a two-step approach for autonomous drone racing that does not require information about the race track (i.e., number of gates, their position and orientation), only the drone’s position in the arena, which could be obtained with GPS, a motion capture system or visual SLAM. We use a neural pilot, trained to regress basic flight commands from camera images where a gate is observed, to enable a drone to navigate the unknown race track autonomously, although at a low speed. During this navigation stage, we use a Single Shot Detector to visually detect the gates. The latter is used to identify the drone’s positions before and after crossing the gate. Once discovered, these positions are used as waypoints in a flight controller to perform a much faster flight to navigate throughout the race track. This approach resembles how human pilots train on an unknown race track, performing several laps to discover key areas where the drone must increase or decrease its speed to cross all the gates successfully. Our approach has been evaluated in the RotorS simulator, comparing it with the performance of a human pilot and obtaining very similar time results.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Cabrera-Ponce, A.A., Rojas-Perez, L.O., Carrasco-Ochoa, J.A., Martinez-Trinidad, J.F., Martinez-Carranza, J.: Gate detection for micro aerial vehicles using a single shot detector. IEEE Lat. Am. Trans. 17(12), 2045–2052 (2019)
Cocoma-Ortega, J.A., Rojas-Perez, L.O., Cabrera-Ponce, A.A., Martinez-Carranza, J.: Overcoming the blind spot in cnn-based gate detection for autonomous drone racing. In: 2019 Workshop on Research, Education and Development of Unmanned Aerial Systems (RED UAS), pp. 253–259. IEEE (2019)
Cocoma-Ortega, J.A., Martinez-Carranza, J.: A cnn based drone localisation approach for autonomous drone racing. In: 11th International Micro Air Vehicle Competition and Conference (2019)
Cocoma-Ortega, J.A., Martínez-Carranza, J.: Towards high-speed localisation for autonomous drone racing. In: Mexican International Conference on Artificial Intelligence, pp. 740–751. Springer (2019)
Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: Monoslam: real-time single camera slam. IEEE Trans. Pattern Anal. Mach. Intell. 29(6), 1052–1067 (2007)
Foehn, P., et al.: Alphapilot: autonomous drone racing. arXiv preprint arXiv:2005.12813 (2020)
Foehn, P., Romero, A., Scaramuzza, D.: Time-optimal planning for quadrotor waypoint flight. Sci. Robot. 6(56), eabh1221 (2021)
Furrer, F., Burri, M., Achtelik, M., Siegwart, R.: RotorS—a modular gazebo MAV simulator framework. In: Koubaa, A. (ed.) Robot Operating System (ROS). SCI, vol. 625, pp. 595–625. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-26054-9_23
Jung, S., Hwang, S., Shin, H., Shim, D.H., et al.: Perception, guidance, and navigation for indoor autonomous drone racing using deep learning. IEEE Robot. Autom. Lett. 3(3), 2539–2544 (2018)
Jung, S., Lee, H., Hwang, S., Shim, D.H.: Real time embedded system framework for autonomous drone racing using deep learning techniques. In: 2018 AIAA Information Systems-AIAA Infotech@ Aerospace, p. 2138 (2018)
Kaufmann, E., Gehrig, M., Foehn, P., Ranftl, R., Dosovitskiy, A., Koltun, V., Scaramuzza, D.: Beauty and the beast: Optimal methods meet learning for drone racing. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 690–696. IEEE (2019)
Kaufmann, E., Loquercio, A., Ranftl, R., Dosovitskiy, A., Koltun, V., Scaramuzza, D., et al.: Deep drone racing: Learning agile flight in dynamic environments. In: Conference on Robot Learning, pp. 133–145. PMLR (2018)
Li, S., De Wagter, C., de Visser, C., Chu, Q., de Croon, G., et al.: In-flight model parameter and state estimation using gradient descent for high-speed flight. Int. J. Micro Air Vehicles 11, 1756829319833685 (2019)
Li, S., van der Horst, E., Duernay, P., De Wagter, C., de Croon, G.C., et al.: Visual model-predictive localization for computationally efficient autonomous racing of a 72-g drone. J. Field Robot. (2020)
Li, S., Ozo, M.M., De Wagter, C., de Croon, G.C., et al.: Autonomous drone race: a computationally efficient vision-based navigation and control strategy. Robotics and Autonomous Systems, p. 103621 (2020)
Liu, W., et al.: SSD: single shot MultiBox detector. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9905, pp. 21–37. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46448-0_2
Madaan, R., et al.: Airsim drone racing lab, pp. 177–191 (2020)
Martinez-Carranza, J., Rojas-Perez, L.O.: Warehouse inspection with an autonomous micro air vehicle. Unmanned Systems, pp. 1–14 (2022)
Moon, H., et al.: Challenges and implemented technologies used in autonomous drone racing. Intel. Serv. Robot. 12(2), 137–148 (2019). https://doi.org/10.1007/s11370-018-00271-6
Moon, H., Sun, Y., Baltes, J., Kim, S.J., et al.: The iros 2016 competitions [competitions]. IEEE Robot. Autom. Mag. 24(1), 20–29 (2017)
Pfeiffer, C., Scaramuzza, D.: Expertise affects drone racing performance. arXiv preprint arXiv:2109.07307 (2021)
Pfeiffer, C., Scaramuzza, D.: Human-piloted drone racing: visual processing and control. IEEE Robot. Autom. Lett. 6(2), 3467–3474 (2021)
Rojas-Perez, L.O., Martinez-Carranza, J.: Deeppilot: a cnn for autonomous drone racing. Sensors 20(16), 4524 (2020)
Sanket, N.J., Singh, C., Ganguly, K., Fermuller, C., Aloimonos, Y.: Gapflyt: active vision based minimalist structure-less gap detection for quadrotor flight. IEEE Robotics and Automation Letters (2018)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Rojas-Perez, L.O., Martinez-Carranza, J. (2022). Where Are the Gates: Discovering Effective Waypoints for Autonomous Drone Racing. In: Bicharra Garcia, A.C., Ferro, M., Rodríguez Ribón, J.C. (eds) Advances in Artificial Intelligence – IBERAMIA 2022. IBERAMIA 2022. Lecture Notes in Computer Science(), vol 13788. Springer, Cham. https://doi.org/10.1007/978-3-031-22419-5_30
Download citation
DOI: https://doi.org/10.1007/978-3-031-22419-5_30
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-22418-8
Online ISBN: 978-3-031-22419-5
eBook Packages: Computer ScienceComputer Science (R0)