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.

翻译：葡萄园中的可靠定位受到行级感知混淆的阻碍：平行的作物行产生几乎相同的LiDAR观测，导致仅基于几何和基于视觉的SLAM系统收敛至错误的行间通道，尤其在端头转弯区域。本文提出一种语义地标粒子滤波器（SLPF），将树干与立柱地标检测与二维LiDAR集成于概率定位框架中。检测到的树干被转换为语义墙体，形成嵌入测量模型的结构化行边界，以增强相邻行间的区分能力。GNSS作为轻量级先验信息被纳入，可在语义观测稀疏时稳定定位。在10行葡萄园中的实地实验表明，该方法相对于仅几何方法（AMCL）、基于视觉方法（RTAB-Map）及GNSS基线均取得持续改进。与AMCL相比，SLPF在两个遍历方向上分别将绝对位姿误差降低22%和65%；相对于带噪声GNSS基线，绝对位姿误差分别减少65%和61%。行识别正确率从0.67提升至0.73，平均横向跟踪误差从1.40米降至1.26米。这些结果表明，在测量模型中嵌入行级结构语义能够实现高度重复的室外农业环境中的鲁棒定位。