Vision-only UAV State Estimation for Fast Flights Without External Localization Systems

Описание: This is a video attachment for manuscript: https://arxiv.org/abs/2602.01860
Vision-only UAV State Estimation for Fast Flights Without External Localization Systems: A2RL Drone Racing Finalist Approach

Visit our webpage for more details: https://mrs.fel.cvut.cz/papers/vision...

Abstract:
Fast flights with aggressive maneuvers in cluttered GNSS-denied environments require fast, reliable, and accurate UAV state estimation. In this paper, we present an approach for onboard state estimation of a high-speed UAV using a monocular RGB camera and an IMU. Our approach fuses data from Visual–Inertial Odometry (VIO), an onboard landmark-based camera measurement system, and an IMU to produce an accurate state estimate. Using onboard measurement data, we estimate and compensate for VIO drift through a novel mathematical drift model. State-of-the-art approaches often rely on more complex hardware (e.g., stereo cameras or rangefinders) and use uncorrected drifting VIO velocities, orientation, and angular rates, leading to errors during fast maneuvers. In contrast, our method corrects all VIO states (position, orientation, linear and angular velocity), resulting in accurate state estimation even during rapid and dynamic motion. Our approach was thoroughly validated through 1600 simulations and numerous real-world experiments. Furthermore, we applied the proposed method in the A2RL Drone Racing Challenge 2025, where our team advanced to the final four out of 210 teams and earned a medal.

Keywords:
Localization, Sensor Fusion, Visual-Inertial SLAM, UAV, Drone Racing

--------------------------------------------------------------------------------------------------------------------------------------------------------------
An MRS open-source research UAV platform was used for experiments presented in this video. See http://mrs.felk.cvut.cz/system for details and the source code of the MRS UAV platform, which enables all essential capabilities for research, development, and testing of novel methods. For publications describing the applied system and control stack, see:
Tomas Baca, Matej Petrlik, Matous Vrba, Vojtech Spurny, Robert Penicka, Daniel Hert and Martin Saska, “The MRS UAV System: Pushing the Frontiers of Reproducible Research, Real-world Deployment, and Education with Autonomous Unmanned Aerial Vehicles,” Journal of Intelligent & Robotic Systems 102(26):1–28, May 2021. (https://link.springer.com/article/10....

This work was accomplished by the MRS group at CTU in Prague http://mrs.felk.cvut.cz . For more experiments with the MRS UAV research platforms, see http://mrs.felk.cvut.cz/publications

--------------------------------------------------------------------------------------------------------------------------------------------------------------
0:00 Intro
0:43 VIO Drift Problem
1:11 State of the Art
1:33 Diagram of Our Method
2:02 Methodology
2:19 Autonomous Drone Racing (A2RL)
3:06 Outdoor Track Flight
3:44 Results
4:11 Conclusion