ROCVDec 17, 2025

BEV-Patch-PF: Particle Filtering with BEV-Aerial Feature Matching for Off-Road Geo-Localization

arXiv:2512.15111v11 citationsh-index: 14
Originality Incremental advance
AI Analysis

This addresses the problem of accurate robot localization in off-road environments under challenging conditions like dense canopy and shadow, representing a strong domain-specific improvement.

The paper tackles GPS-free sequential geo-localization for off-road robots by integrating a particle filter with learned bird's-eye-view and aerial feature maps, achieving 7.5x lower absolute trajectory error on seen routes and 7.0x lower on unseen routes compared to a baseline.

We propose BEV-Patch-PF, a GPS-free sequential geo-localization system that integrates a particle filter with learned bird's-eye-view (BEV) and aerial feature maps. From onboard RGB and depth images, we construct a BEV feature map. For each 3-DoF particle pose hypothesis, we crop the corresponding patch from an aerial feature map computed from a local aerial image queried around the approximate location. BEV-Patch-PF computes a per-particle log-likelihood by matching the BEV feature to the aerial patch feature. On two real-world off-road datasets, our method achieves 7.5x lower absolute trajectory error (ATE) on seen routes and 7.0x lower ATE on unseen routes than a retrieval-based baseline, while maintaining accuracy under dense canopy and shadow. The system runs in real time at 10 Hz on an NVIDIA Tesla T4, enabling practical robot deployment.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes