BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images
This addresses the problem of accurate global localization in varied real-world environments for robotics and autonomous systems, representing an incremental improvement over existing scene-agnostic pipelines.
The paper tackles LiDAR global localization by introducing BEV-SLD, a self-supervised method that uses bird's-eye-view images to detect scene-specific landmarks, achieving robust localization across diverse environments like campus, industrial, and forest settings with strong performance compared to state-of-the-art methods.
We present BEV-SLD, a LiDAR global localization method building on the Scene Landmark Detection (SLD) concept. Unlike scene-agnostic pipelines, our self-supervised approach leverages bird's-eye-view (BEV) images to discover scene-specific patterns at a prescribed spatial density and treat them as landmarks. A consistency loss aligns learnable global landmark coordinates with per-frame heatmaps, yielding consistent landmark detections across the scene. Across campus, industrial, and forest environments, BEV-SLD delivers robust localization and achieves strong performance compared to state-of-the-art methods.