针对自动驾驶高精地图构建难题，提出高效稀疏专家模型。
MapExpert: Online HD Map Construction with Simple and Efficient Sparse Map Element Expert
- 用稀疏专家模块分别处理不同道路元素，提升描述精度
- 在nuScenes和Argoverse2上达到当前最佳性能，推理效率高
- 适合需要实时高精地图更新的自动驾驶系统研发者
构建在线高精（HD）地图对自动驾驶系统的静态环境感知至关重要。现有方法通常使用统一模型检测矢量化高精地图元素，但常忽略不同非立方体地图元素的差异特征，导致区分困难。为此，我们提出基于专家的在线高精地图方法MapExpert。MapExpert通过路由器分发稀疏专家，精准描述各类非立方体地图元素。同时，设计辅助平衡损失函数，使专家负载均衡。此外，理论分析了主流鸟瞰图（BEV）特征时序融合方法的局限性，提出一种高效时序融合模块——可学习加权移动衰减（Learnable Weighted Moving Descentage），有效将历史信息融入最终BEV特征。结合增强的切片头分支，MapExpert在nuScenes和Argoverse2数据集上均实现顶尖性能，并保持良好效率。
原文摘要 · Abstract (English)
Constructing online High-Definition (HD) maps is crucial for the static environment perception of autonomous driving systems (ADS). Existing solutions typically attempt to detect vectorized HD map elements with unified models; however, these methods often overlook the distinct characteristics of different non-cubic map elements, making accurate distinction challenging. To address these issues, we introduce an expert-based online HD map method, termed MapExpert. MapExpert utilizes sparse experts, distributed by our routers, to describe various non-cubic map elements accurately. Additionally, we propose an auxiliary balance loss function to distribute the load evenly across experts. Furthermore, we theoretically analyze the limitations of prevalent bird's-eye view (BEV) feature temporal fusion methods and introduce an efficient temporal fusion module called Learnable Weighted Moving Descentage. This module effectively integrates relevant historical information into the final BEV features. Combined with an enhanced slice head branch, the proposed MapExpert achieves state-of-the-art performance and maintains good efficiency on both nuScenes and Argoverse2 datasets.
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。