发表机构
Bosch Research North America; Bosch Center for Artificial Intelligence (BCAI); The Ohio State University（博世北美研究院; 博世人工智能中心; 俄亥俄州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MapMergeLLM，利用大语言模型将矢量化地图聚合建模为条件序列生成，通过合成数据训练和坐标分词器及线级关联损失，在多个数据集上超越传统聚合方法。
AI 中文摘要
大规模矢量化高清地图提供了结构化道路信息，这对于自动驾驶中的感知、定位和规划至关重要。构建此类地图需要将沿车辆轨迹收集的噪声、碎片化和重叠的局部预测聚合为连贯的全局地图。现有的聚合方法通常依赖手工规则进行片段关联和细化。然而，固定的阈值集合无法有效处理道路结构和预测误差的变化，往往需要针对检测器进行特定调整或手动修改。为解决这一局限，我们提出MapMergeLLM，一种数据驱动的框架，将矢量化地图聚合表述为基于大语言模型的条件序列生成。给定序列化的局部矢量化地图，我们的模型直接预测聚合后的全局地图折线。为减少对任何特定上游检测器的依赖，我们使用由干净矢量地图生成的合成局部地图进行训练，并通过添加模拟代表性预测误差的损坏来生成。我们进一步引入带有几何感知预训练的坐标分词器，以精确表示地图坐标。此外，我们提出一种线级关联损失，显式监督同一地图元素的局部观测之间的对应关系。在Argoverse2和nuScenes上使用多个近期上游检测器的实验表明，MapMergeLLM在无需检测器特定重训练的情况下，显著优于基于启发式和优化的聚合基线。
英文摘要
Large-scale vectorized HD maps provide structured road information that is essential for perception, localization, and planning in autonomous driving. Constructing such maps requires aggregating noisy, fragmented, and overlapping local predictions collected along a vehicle trajectory into a coherent global map. Existing aggregation methods typically rely on hand-crafted rules for fragment association and refinement. However, a fixed set of thresholds cannot effectively handle variations in road structures and prediction errors, often requiring detector-specific tuning or manual adjustment. To address this limitation, we propose MapMergeLLM, a data-driven framework that formulates vectorized map aggregation as conditional sequence generation with a large language model. Given serialized local vectorized maps, our model directly predicts the aggregated global map polylines. To reduce dependence on any particular upstream detector, we train the model on synthetic local maps generated from clean vector maps using corruptions that simulate representative prediction errors. We further introduce a coordinate tokenizer with geometry-aware pretraining to precisely represent map coordinates. In addition, we propose a line-level association loss that explicitly supervises correspondences between local observations of the same map element. Experiments on Argoverse2 and nuScenes using multiple recent upstream detectors demonstrate that MapMergeLLM substantially outperforms heuristic and optimization-based aggregation baselines without detector-specific retraining.
