计算机科学
嵌入
集合(抽象数据类型)
趋同(经济学)
过程(计算)
匹配(统计)
编码(集合论)
排列(音乐)
推论
端到端原则
地图匹配
路线图
要素(刑法)
理论计算机科学
算法
人工智能
数学
政治学
声学
经济增长
地图学
全球定位系统
电信
统计
操作系统
物理
经济
程序设计语言
法学
地理
作者
Bencheng Liao,Shaoyu Chen,Yunchi Zhang,Bo Jiang,Qian Zhang,Wenyu Liu,Chang Huang,Xinggang Wang
出处
期刊:Cornell University - arXiv
日期:2023-01-01
被引量:5
标识
DOI:10.48550/arxiv.2308.05736
摘要
High-definition (HD) map provides abundant and precise static environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system. In this paper, we present \textbf{Map} \textbf{TR}ansformer, an end-to-end framework for online vectorized HD map construction. We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process. We design a hierarchical query embedding scheme to flexibly encode structured map information and perform hierarchical bipartite matching for map element learning. To speed up convergence, we further introduce auxiliary one-to-many matching and dense supervision. The proposed method well copes with various map elements with arbitrary shapes. It runs at real-time inference speed and achieves state-of-the-art performance on both nuScenes and Argoverse2 datasets. Abundant qualitative results show stable and robust map construction quality in complex and various driving scenes. Code and more demos are available at \url{https://github.com/hustvl/MapTR} for facilitating further studies and applications.
科研通智能强力驱动
Strongly Powered by AbleSci AI