Dual Pose-Graph Semantic Localization for Vision-Based Autonomous Drone Racing

TL;DR

This paper introduces a dual pose-graph system combining odometry and semantic detections to improve real-time localization for autonomous drone racing, outperforming traditional SLAM methods under extreme conditions.

Contribution

The novel dual pose-graph architecture effectively fuses multiple observations to enhance accuracy and robustness in high-speed drone racing scenarios.

Findings

Achieved 56% to 74% reduction in ATE compared to standalone VIO.

Dual-graph architecture outperforms single-graph baseline by 10-12% in accuracy.

System reduces odometry drift by up to 4.2 meters per lap during real-time flight.

Abstract

Autonomous drone racing demands robust real-time localization under extreme conditions: high-speed flight, aggressive maneuvers, and payload-constrained platforms that often rely on a single camera for perception. Existing visual SLAM systems, while effective in general scenarios, struggle with motion blur and feature instability inherent to racing dynamics, and do not exploit the structured nature of racing environments. In this work, we present a dual pose-graph architecture that fuses odometry with semantic detections for robust localization. A temporary graph accumulates multiple gate observations between keyframes and optimizes them into a single refined constraint per landmark, which is then promoted to a persistent main graph. This design preserves the information richness of frequent detections while preventing graph growth from degrading real-time performance. The system is designed to be sensor-agnostic, although in this work we validate it using monocular visual-inertial odometry and visual gate detections. Experimental evaluation on the TII-RATM dataset shows a 56% to 74% reduction in ATE compared to standalone VIO, while an ablation study confirms that the dual-graph architecture achieves 10% to 12% higher accuracy than a single-graph baseline at identical computational cost. Deployment in the A2RL competition demonstrated that the system performs real-time onboard localization during flight, reducing the drift of the odometry baseline by up to 4.2 m per lap.