Semantic Landmark Particle Filter for Robot Localisation in Vineyards

2026-03-11

AI Summary

This study addresses the challenge of robot localization failure in vineyards caused by repetitive inter-row structures, particularly during headland turns where vehicles often drift into adjacent rows. To overcome this, the authors propose a particle filter–based localization method that fuses semantic landmarks from trunks and poles, 2D LiDAR measurements, and lightweight GNSS priors. The key innovation lies in explicitly embedding row-level structural semantics into the measurement model through “semantic walls” that delineate crop row boundaries, thereby significantly enhancing inter-row distinguishability. Experimental results demonstrate that the proposed approach reduces absolute pose error by 22%–65% compared to AMCL and NoisyGNSS baselines, achieves a row correctness rate of 0.73, and lowers lateral error to 1.26 meters, substantially improving localization robustness in repetitive agricultural environments.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Search and Optimization: Local Search

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Reliable localisation in vineyards is hindered by row-level perceptual aliasing: parallel crop rows produce nearly identical LiDAR observations, causing geometry-only and vision-based SLAM systems to converge towards incorrect corridors, particularly during headland transitions. We present a Semantic Landmark Particle Filter (SLPF) that integrates trunk and pole landmark detections with 2D LiDAR within a probabilistic localisation framework. Detected trunks are converted into semantic walls, forming structural row boundaries embedded in the measurement model to improve discrimination between adjacent rows. GNSS is incorporated as a lightweight prior that stabilises localisation when semantic observations are sparse. Field experiments in a 10-row vineyard demonstrate consistent improvements over geometry-only (AMCL), vision-based (RTAB-Map), and GNSS baselines. Compared to AMCL, SLPF reduces Absolute Pose Error by 22% and 65% across two traversal directions; relative to a NoisyGNSS baseline, APE decreases by 65% and 61%. Row correctness improves from 0.67 to 0.73, while mean cross-track error decreases from 1.40 m to 1.26 m. These results show that embedding row-level structural semantics within the measurement model enables robust localisation in highly repetitive outdoor agricultural environments.

Problem

• perceptual aliasing
• robot localisation
• vineyards
• LiDAR
• semantic landmarks

Innovation

• Semantic Landmark
• Particle Filter
• Perceptual Aliasing
• Agricultural Robotics
• LiDAR-based Localization