用树干和柱子做语义地标，让机器人在葡萄园里不迷路。
Semantic Landmark Particle Filter for Robot Localisation in Vineyards
- 融合激光雷达与树干/柱子检测，用语义结构区分相似行道。
- 相比纯几何方法，定位误差降低22%~65%，跨行误差减小14%。
- 适合重复性强的农田环境，尤其对低精度定位系统有显著提升。
葡萄园中因行间感知歧义（平行种植行产生几乎相同的激光雷达观测）导致几何与视觉SLAM系统在转弯区易误收敛至错误通道。本文提出语义地标粒子滤波器（SLPF），将树干与立柱检测结果转化为语义墙，嵌入测量模型以增强相邻行间的区分度；同时引入轻量级GNSS作为先验，在语义观测稀疏时稳定定位。在10行葡萄园实地测试中，相较几何仅依赖的AMCL、基于视觉的RTAB-Map及含噪GNSS基线，SLPF表现显著提升：绝对位姿误差（APE）分别降低22%与65%（两个方向），跨行正确率由0.67升至0.73，平均横向误差从1.40米降至1.26米。结果表明，在高度重复的户外农业环境中，将行级结构语义嵌入测量模型可实现鲁棒定位。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。