High-definition (HD) map is crucial for autonomous driving systems. Most
existing works design map elements detection heads based on the DETR decoder.
However, the initial queries lack integration with the physical location
feature of map elements, and vanilla self-attention entails high computational
complexity. Therefore, we propose EAN-MapNet for Efficiently constructing HD
map using Anchor Neighborhoods. Firstly, we design query units based on the
physical location feature of anchor neighborhoods. Non-neighborhood central
anchors effectively assist the neighborhood central anchors in fitting to the
target points, significantly improving the prediction accuracy. Then, we
introduce grouped local self-attention (GL-SA), which innovatively utilizes
local queries as the medium for feature interaction, thereby substantially
reducing the computational complexity of self-attention while facilitating
ample feature interaction among queries. On nuScenes dataset, EAN-MapNet
achieves a state-of-the-art performance with 63.0 mAP after training for 24
epochs. Furthermore, it considerably reduces memory consumption by 8198M
compared to the baseline.

在自动驾驶系统中，高清地图对运行是至关重要的。本文提出了 EAN-MapNet 方法，通过锚点邻域的高效构建来构建高清地图。利用物理位置特征和分组本地自注意力的方法，可以显著提高预测准确性并降低自注意力的计算复杂度。在 nuScenes 数据集上，EAN-MapNet 在训练 24 个时期后达到了 63.0 的 mAP，且相比基线方法大大降低了内存消耗。

EAN-MapNet：高效矢量化高清地图构建方法与窗口邻域

EAN-MapNet: Efficient Vectorized HD Map Construction with Anchor  Neighborhoods

In autonomous driving, the high-definition (HD) map plays a crucial role in
localization and planning. Recently, several methods have facilitated
end-to-end online map construction in DETR-like frameworks. However, little
attention has been paid to the potential capabilities of exploring the query
mechanism. This paper introduces MapQR, an end-to-end method with an emphasis
on enhancing query capabilities for constructing online vectorized maps.
Although the map construction is essentially a point set prediction task, MapQR
utilizes instance queries rather than point queries. These instance queries are
scattered for the prediction of point sets and subsequently gathered for the
final matching. This query design, called the scatter-and-gather query, shares
content information in the same map element and avoids possible inconsistency
of content information in point queries. We further exploit prior information
to enhance an instance query by adding positional information embedded from
their reference points. Together with a simple and effective improvement of a
BEV encoder, the proposed MapQR achieves the best mean average precision (mAP)
and maintains good efficiency on both nuScenes and Argoverse 2. In addition,
integrating our query design into other models can boost their performance
significantly. The code will be available at this https URL

一个以增强查询功能为重点的端到端方法（MapQR），用于构建在线矢量地图。通过使用散开并聚合的查询设计以及添加来自参考点的位置信息来改进实例查询，MapQR 实现了最佳的平均精度 (mAP) 并且在 nuScenes 和 Argoverse 2 上具有良好的效率。

利用增强的点集查询进行矢量化地图构建

Leveraging Enhanced Queries of Point Sets for Vectorized Map  Construction

High-definition (HD) Map systems will play a pivotal role in advancing
autonomous driving to a higher level, thanks to the significant improvement
over traditional two-dimensional (2D) maps. Creating an HD Map requires a huge
amount of on-road and off-road data. Typically, these raw datasets are
collected and uploaded to cloud-based HD map service providers through
vehicular networks. Nevertheless, there are challenges in transmitting the raw
data over vehicular wireless channels due to the dynamic topology. As the
number of vehicles increases, there is a detrimental impact on service quality,
which acts as a barrier to a real-time HD Map system for collaborative driving
in Autonomous Vehicles (AV). In this paper, to overcome network congestion, a
Q-learning coverage-time-awareness algorithm is presented to optimize the
quality of service for vehicular networks and HD map updates. The algorithm is
evaluated in an environment that imitates a dynamic scenario where vehicles
enter and leave. Results showed an improvement in latency for HD map data of
$75\%$, $73\%$, and $10\%$ compared with IEEE802.11p without Quality of Service
(QoS), IEEE802.11 with QoS, and IEEE802.11p with new access category (AC) for
HD map, respectively.

高清地图技术在自动驾驶中扮演关键角色，本论文提出了一种 Q-learning 算法来优化车载网络和高清地图更新，以解决网络拥塞和服务质量问题，实验结果显示，相较于其他方案，该算法显著提高了高清地图数据的延迟性能。