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

TL;DR

This paper introduces ADR-VINS, a robust monocular visual-inertial state estimator for drone racing that is efficient and resilient to perceptual challenges, along with ADR-FGO for high-fidelity offline trajectory evaluation.

Contribution

It presents a novel tightly-coupled filter-based approach that handles minimal feature observations and robust outlier rejection, plus an offline factor-graph framework for performance analysis.

Findings

ADR-VINS achieves 0.134 m RMS translation error on TII-RATM dataset.

ADR-FGO provides a 0.060 m high-fidelity reference trajectory.

System maintains stability during high-speed, high-maneuver drone flights.

Abstract

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 0.134 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.