Semantic-Aware Particle Filter for Reliable Vineyard Robot Localisation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: de Silva, Rajitha, Cox, Jonathan, Heselden, James R., Popovic, Marija, Cadena, Cesar, Polvara, Riccardo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914051414556672
author de Silva, Rajitha
Cox, Jonathan
Heselden, James R.
Popovic, Marija
Cadena, Cesar
Polvara, Riccardo
author_facet de Silva, Rajitha
Cox, Jonathan
Heselden, James R.
Popovic, Marija
Cadena, Cesar
Polvara, Riccardo
contents Accurate localisation is critical for mobile robots in structured outdoor environments, yet LiDAR-based methods often fail in vineyards due to repetitive row geometry and perceptual aliasing. We propose a semantic particle filter that incorporates stable object-level detections, specifically vine trunks and support poles into the likelihood estimation process. Detected landmarks are projected into a birds eye view and fused with LiDAR scans to generate semantic observations. A key innovation is the use of semantic walls, which connect adjacent landmarks into pseudo-structural constraints that mitigate row aliasing. To maintain global consistency in headland regions where semantics are sparse, we introduce a noisy GPS prior that adaptively supports the filter. Experiments in a real vineyard demonstrate that our approach maintains localisation within the correct row, recovers from deviations where AMCL fails, and outperforms vision-based SLAM methods such as RTAB-Map.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18342
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Semantic-Aware Particle Filter for Reliable Vineyard Robot Localisation
de Silva, Rajitha
Cox, Jonathan
Heselden, James R.
Popovic, Marija
Cadena, Cesar
Polvara, Riccardo
Robotics
Computer Vision and Pattern Recognition
Accurate localisation is critical for mobile robots in structured outdoor environments, yet LiDAR-based methods often fail in vineyards due to repetitive row geometry and perceptual aliasing. We propose a semantic particle filter that incorporates stable object-level detections, specifically vine trunks and support poles into the likelihood estimation process. Detected landmarks are projected into a birds eye view and fused with LiDAR scans to generate semantic observations. A key innovation is the use of semantic walls, which connect adjacent landmarks into pseudo-structural constraints that mitigate row aliasing. To maintain global consistency in headland regions where semantics are sparse, we introduce a noisy GPS prior that adaptively supports the filter. Experiments in a real vineyard demonstrate that our approach maintains localisation within the correct row, recovers from deviations where AMCL fails, and outperforms vision-based SLAM methods such as RTAB-Map.
title Semantic-Aware Particle Filter for Reliable Vineyard Robot Localisation
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.18342