Onboard UAV State Estimation for Fast Flights Without External Localization Systems: A2RL Drone Racing Finalist Approach

Filip Novák; Matěj Petrlík; Matej Novosad; Parakh M. Gupta; Robert Pěnička; Martin Saska

cs.ROFeb 2, 2026

Onboard UAV State Estimation for Fast Flights Without External Localization Systems: A2RL Drone Racing Finalist Approach

Authors: Filip Novák, Matěj Petrlík, Matej Novosad, Parakh M. Gupta, Robert Pěnička, Martin Saska

Organizations: Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic.

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.

Figures & tables

Figure 1: Long-exposure photo of drones carrying blue lights taken during a race flight at the A2RL Drone Racing Challenge 2025.

Panel of Figure 2 — Figure 2: This figure presents the pipeline diagram of the estimation approach proposed in this paper, highlighted by the light blue dotted rectangle and integrated into our drone racing framework. The High-level mission planning block provides the desired position and heading references $(\mathbf{r}_{d},\eta_{d})$ for the UAV to follow the race track. These references are passed to the Reference tracker , which generates a smooth and dynamically feasible reference $\bm{\chi}_{d}$ for the Reference controller . The Reference controller computes the desired thrust and angular velocities $(\bm{\omega}_{d},~T_{d})$ for the embedded flight controller, which then sends actuator commands $\bm{\tau}_{cm}$ to the UAV actuators . The VIO algorithm uses IMU data and onboard camera images to estimate the UAV position $\mathbf{x}$ , orientation $\mathbf{R}$ , linear velocity $\dot{\mathbf{x}}$ , and angular velocity $\bm{\omega}$ . The VIO drift estimator estimates the drift in the VIO states using position $\mathbf{x}$ and orientation $\mathbf{R}$ measurements from the Landmark detector . The State estimator fuses data from the IMU , VIO drift estimator , and VIO algorithm to estimate the UAV position, orientation, and linear and angular velocities $(\mathbf{x},\dot{\mathbf{x}},\mathbf{R},\bm{\omega})$ .

Figure 3: The depiction of coordinate frames consisting of the world frame

\mathcal{W}{}

, UAV body frame

\mathcal{B}_{w}{}

expressed in the

\mathcal{W}{}

frame, VIO frame

\mathcal{V}{}

, and UAV body frame

\mathcal{B}_{v}{}

expressed in the

\mathcal{V}{}

frame. The relative position and orientation between the

\mathcal{W}{}

frame and the

\mathcal{V}{}

frame are represented by

\mathbf{r}_{\text{init}}^{w}

. The UAV position and orientation in

\mathcal{W}{}

frame are denoted as

\mathbf{r}_{\text{gt}}^{w}

. The UAV position and orientation estimated by the VIO algorithm are provided in the

\mathcal{V}{}

frame and denoted as

\mathbf{r}_{\text{vio}}^{v}

. The vector

\mathbf{r}_{\text{vio}}^{w}

represents the VIO -estimated UAV position and orientation expressed in the

\mathcal{W}{}

frame. The VIO drift is expressed as

\mathbf{r}_{\text{drift}}^{w}

$\bm{\sigma^{2}_{\mathbf{p}_{\text{ld}}}}$ [ $\text{\,}\mathrm{m}$ ]		0.001	0.01	0.1	1.0	0.001	0.01	0.1	1.0
$\bm{\sigma^{2}_{\psi_{\text{ld}}}}$ [ $\text{\,}\mathrm{rad}$ ]		0.001	0.01	0.1	1.0	0.001	0.01	0.1	1.0
$\bm{\tau_{\text{{d}}}}$ [ $\text{\,}\mathrm{ms}$ ]	State	Our approach				VIO
0	$\mathbf{p}$ [ $\text{\,}\mathrm{m}$ ]	0.35	0.40	0.45	1.11	6.39	7.55	8.68	8.44
	$\mathbf{\Theta}$ [ $\text{\,}\mathrm{rad}$ ]	0.04	0.04	0.09	0.57	0.23	0.23	0.26	0.29
	$\mathbf{v}$ [ $\text{\,}\mathrm{m}\text{\,}{\mathrm{s}}^{-1}$ ]	0.96	1.00	1.09	1.40	1.27	1.30	1.49	1.57
	$\bm{\omega}$ [ $\text{\,}\mathrm{rad}\text{\,}{\mathrm{s}}^{-1}$ ]	0.24	0.23	0.24	0.24	1.13	1.15	1.11	1.09

Table 1: RMSE results from the simulations.

Figure 4: Custom-built outdoor track used to verify our approach.

Figure 6: 3D plot of the estimated UAV position using our approach, with color indicating the UAV speed. The VIO position is shown in grey. Measurements from the Landmark detector are represented as circles, with green color indicating confidence, and the race gates are shown as black circles.

Figure 5: Top view of the outdoor track showing the RTK states, results of our approach, VIO states, and data from the Landmark detector (LM det.).

Method	State	RMSE	Mean	Std. Dev.	Max
Our approach	$\mathbf{p}$ [ $\text{\,}\mathrm{m}$ ]	0.543	0.477	0.260	1.490
	$\mathbf{\Theta}$ [ $\text{\,}\mathrm{rad}$ ]	0.092	0.077	0.050	0.229
	$\mathbf{v}$ [ $\text{\,}\mathrm{m}\text{\,}{\mathrm{s}}^{-1}$ ]	1.262	1.036	0.722	3.689
	$\bm{\omega}$ [ $\text{\,}\mathrm{rad}\text{\,}{\mathrm{s}}^{-1}$ ]	0.103	0.074	0.071	0.709
Foehn et al. [ 9 ]	$\mathbf{p}$ [ $\text{\,}\mathrm{m}$ ]	0.645	0.535	0.359	2.396
	$\mathbf{\Theta}$ [ $\text{\,}\mathrm{rad}$ ]	0.179	0.163	0.074	0.343

Table 2: RMSE, mean error, standard deviation of the error, and maximum error of estimated UAV states using our approach compared to state-of-the-art, VIO, and Landmark detector.

Figure 7: Estimated UAV states during the A2RL finals using our approach.

Robot State Estimation

Robot state estimation infers a robot’s position, motion, orientation, and internal configuration from noisy sensors and physical constraints.

See all 200 papers

Robust Tightly-Coupled Filter-Based Monocular Visual-Inertial State Estimation and Graph-Based Evaluation for Autonomous Drone Racing
Mar 3, 2026Maulana Bisyir Azhari, Donghun Han, Sung Jun Park +1Autonomous Drone Racing Error-State Kalman Filtering
Unmanned Systems Research Group (USRG), School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea.
Towards Agile Vision-Based Multi-UAV Flight: Revisiting State Estimation
Sep 30, 2026Michal Pliska, Matouš Vrba, Ondřej Víta +3Aerial Robotics Kalman Filtering
Multi-robot Systems Group, Faculty of Electrical Engineering, Czech Technical University in Prague, Czech Republic
Motor Angular Speed Preintegration for Multirotor UAV State Estimation
Jun 18, 2026Matěj Petrlík, Filip Novák, Robert Pěnička +1UAV Navigation LiDAR Odometry
Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University in Prague, 166 36, Prague 6, Czech Republic

Mar 3, 2026J/K move · Enter open · S save

Robust Tightly-Coupled Filter-Based Monocular Visual-Inertial State Estimation and Graph-Based Evaluation for Autonomous Drone Racing

Maulana Bisyir Azhari, Donghun Han, Sung Jun Park, David Hyunchul Shim

Unmanned Systems Research Group (USRG), School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, South Korea.

Autonomous Drone Racing Error-State Kalman Filtering Visual-Inertial Odometry Aerial Robotics Kalman Filtering Factor Graph Optimization

Open paper AskPDF arXiv

Autonomous drone racing (ADR) demands state estimation that is simultaneously computationally efficient and resilient to the perceptual degradation experienced during extreme velocity and maneuvers. Traditional frameworks typically rely on conventional visual-inertial pipelines with loosely-coupled gate-based Perspective-n-Points (PnP) corrections that suffer from a rigid requirement for four visible features and information loss in intermediate steps. Furthermore, the absence of GNSS and Motion Capture systems in uninstrumented, competitive racing environments makes the objective evaluation of such systems remarkably difficult. To address these limitations, we propose ADR-VINS, a robust, monocular visual-inertial state estimation framework based on an Error-State Kalman Filter (ESKF) tailored for autonomous drone racing. Our approach integrates direct pixel reprojection errors from gate corners features as innovation terms within the filter. By bypassing intermediate PnP solvers, ADR-VINS maintains valid state updates with as few as two visible corners and utilizes robust reweighting instead of RANSAC-based schemes to handle outliers, enhancing computational efficiency. Furthermore, we introduce ADR-FGO, an offline Factor-Graph Optimization framework to generate high-fidelity reference trajectories that facilitate post-flight performance evaluation and analysis on uninstrumented, GNSS-denied environments. The proposed system is validated using TII-RATM dataset, where ADR-VINS achieves an average RMS translation error of 0.143 m, while ADR-FGO yields 0.060 m as a smoothing-based reference. Finally, ADR-VINS was successfully deployed in the A2RL Drone Championship Season 2, maintaining stable and robust estimation despite noisy detections during high-agility flight at top speeds of 20.9 m/s. We further utilize ADR-FGO for post-flight evaluation in uninstrumented racing environments.

Abstract

Robot State Estimation

Explore similar work

Robust Tightly-Coupled Filter-Based Monocular Visual-Inertial State Estimation and Graph-Based Evaluation for Autonomous Drone Racing

Towards Agile Vision-Based Multi-UAV Flight: Revisiting State Estimation

Motor Angular Speed Preintegration for Multirotor UAV State Estimation