Visual Model-predictive Localization for Computationally Efficient Autonomous Racing of a 72-gram Drone

Drone racing is becoming a popular e-sport all over the world, and beating the best human drone race pilots has quickly become a new major challenge for artificial intelligence and robotics. In this paper, we propose a strategy for autonomous drone racing which is computationally more efficient than navigation methods like visual inertial odometry and simultaneous localization and mapping. This fast light-weight vision-based navigation algorithm estimates the position of the drone by fusing race gate detections with model dynamics predictions. Theoretical analysis and simulation results show the clear advantage compared to Kalman filtering when dealing with the relatively low frequency visual updates and occasional large outliers that occur in fast drone racing. Flight tests are performed on a tiny racing quadrotor named "Trashcan", which was equipped with a Jevois smart-camera for a total of 72g. The test track consists of 3 laps around a 4-gate racing track. The gates spaced 4 meters apart and can be displaced from their supposed position. An average speed of 2m/s is achieved while the maximum speed is 2.6m/s. To the best of our knowledge, this flying platform is the smallest autonomous racing drone in the world and is 6 times lighter than the existing lightest autonomous racing drone setup (420g), while still being one of the fastest autonomous racing drones in the world.

[1]  Vijay Kumar,et al.  Estimation, Control, and Planning for Aggressive Flight With a Small Quadrotor With a Single Camera and IMU , 2017, IEEE Robotics and Automation Letters.

[2]  Sergei Lupashin,et al.  A platform for aerial robotics research and demonstration: The Flying Machine Arena , 2014 .

[3]  Hilbert J. Kappen,et al.  Efficient Optical Flow and Stereo Vision for Velocity Estimation and Obstacle Avoidance on an Autonomous Pocket Drone , 2016, IEEE Robotics and Automation Letters.

[4]  Giuseppe Loianno,et al.  Autonomous navigation of micro aerial vehicles using high-rate and low-cost sensors , 2017, Autonomous Robots.

[5]  Yiannis Aloimonos,et al.  GapFlyt: Active Vision Based Minimalist Structure-Less Gap Detection For Quadrotor Flight , 2018, IEEE Robotics and Automation Letters.

[6]  G. Chang.  Robust Kalman filtering based on Mahalanobis distance as outlier judging criterion , 2014, Journal of Geodesy.

[7]  Mark W. Mueller,et al.  Fusing ultra-wideband range measurements with accelerometers and rate gyroscopes for quadrocopter state estimation , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Jian Wang,et al.  GPS/UWB/MEMS-IMU tightly coupled navigation with improved robust Kalman filter , 2016 .

[9]  Murat Bronz,et al.  Using the Paparazzi UAV System for Scientific Research , 2014 .

[10]  Guido C. H. E. de Croon,et al.  Challenges and implemented technologies used in autonomous drone racing , 2019, Intelligent Service Robotics.

[11]  Mario Sarcinelli-Filho,et al.  Outdoor waypoint navigation with the AR.Drone quadrotor , 2015, 2015 International Conference on Unmanned Aircraft Systems (ICUAS).

[12]  Gene Merewether,et al.  Differential Flatness Transformations for Aggressive Quadrotor Flight , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Luxin Han,et al.  Optimal Trajectory Generation for Quadrotor Teach-and-Repeat , 2019, IEEE Robotics and Automation Letters.

[14]  W. P. M. H. Heemels,et al.  Event- and Deadline-Driven Control of a Self-Localizing Robot With Vision-Induced Delays , 2020, IEEE Transactions on Industrial Electronics.

[15]  Vijay Kumar,et al.  Trajectory Generation and Control for Precise Aggressive Maneuvers with Quadrotors , 2010, ISER.

[16]  Antonio Franchi,et al.  Differential Flatness of Quadrotor Dynamics Subject to Rotor Drag for Accurate Tracking of High-Speed Trajectories , 2017, IEEE Robotics and Automation Letters.

[17]  Dario Izzo,et al.  Learning the optimal state-feedback via supervised imitation learning , 2019, Astrodynamics.

[18]  G. Diderrich,et al.  The Kalman Filter from the Perspective of Goldberger—Theil Estimators , 1985 .

[19]  Balazs Gati,et al.  Open source autopilot for academic research - The Paparazzi system , 2013, 2013 American Control Conference.

[20]  Robert C. Bolles,et al.  Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography , 1981, CACM.

[21]  Vladlen Koltun,et al.  Beauty and the Beast: Optimal Methods Meet Learning for Drone Racing , 2018, 2019 International Conference on Robotics and Automation (ICRA).

[22]  Marcello R. Napolitano,et al.  Flight-Test Evaluation of Sensor Fusion Algorithms for Attitude Estimation , 2012, IEEE Transactions on Aerospace and Electronic Systems.

[23]  Kris Hauser,et al.  Learning Trajectories for Real- Time Optimal Control of Quadrotors , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Vladlen Koltun,et al.  Deep Drone Racing: Learning Agile Flight in Dynamic Environments , 2018, CoRL.

[25]  David Hyunchul Shim,et al.  A direct visual servoing‐based framework for the 2016 IROS Autonomous Drone Racing Challenge , 2018, J. Field Robotics.

[26]  Yu Sun,et al.  The IROS 2016 Competitions [Competitions] , 2017, IEEE Robotics Autom. Mag..

[27]  Guido C. H. E. de Croon,et al.  A novel online model-based wind estimation approach for quadrotor micro air vehicles using low cost MEMS IMUs , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Vijay Kumar,et al.  Minimum snap trajectory generation and control for quadrotors , 2011, 2011 IEEE International Conference on Robotics and Automation.

[29]  Roland Siegwart,et al.  Versatile distributed pose estimation and sensor self-calibration for an autonomous MAV , 2012, 2012 IEEE International Conference on Robotics and Automation.

[30]  Davide Scaramuzza,et al.  Aggressive quadrotor flight through narrow gaps with onboard sensing and computing using active vision , 2016, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[31]  Guido C. H. E. de Croon,et al.  Autonomous drone race: A computationally efficient vision-based navigation and control strategy , 2018, Robotics Auton. Syst..