Summary
Self-driving cars need to understand road features like lanes, signs, and traffic rules to drive safely. The authors explain that while many tasks related to recognizing these features have been studied, the field is split by different approaches and ways to measure success. They organize these studies into three groups based on the type of road information and review how sensing methods and data models have changed over time. They also point out current issues with testing and suggest directions to improve the accuracy and usefulness of road perception systems for driving decisions. This work helps unify how machines see and understand roads to support safer autonomous driving.
What this means in practice
- •For autonomous vehicle engineers: Develop unified road perception models that integrate geometry, function, and traffic rules for better real-time environment understanding.
- •For urban mobility planners: Use insights from road infrastructure perception to design smarter road environments that support automated vehicle navigation.
A survey. It maps existing work.
Authors
Guoyang Zhao, Weiqing Qi, Kai Zhang, Zhihai Bi, Tianshuai Hu, Zeying Gong, Dezong Zhao, Jun Ma
Abstract
Road infrastructure perception is a fundamental component of autonomous driving, as it recovers the structured road elements that define roadway geometry, delimit operational space, and encode traffic regulations. Although individual tasks such as lane detection, drivable-space estimation, traffic-sign recognition, and online map construction have been extensively studied, the field remains fragmented across task definitions, sensing assumptions, output representations, datasets, and evaluation protocols. This survey provides a function-oriented synthesis of road infrastructure perception. We first clarify its scope and organize existing studies into three complementary categories: geometric-structural, functional-spatial, and regulatory-semantic infrastructure. Based on this taxonomy, we review sensing modalities, scene representations, representative methods, benchmarks, and evaluation protocols, emphasizing the field's evolution from image-space recognition toward metric, vectorized, topology-aware, occupancy-based, and rule-grounded scene modeling. We further examine how representation choices affect evaluation and downstream usability, revealing limitations of current benchmarks in relation reasoning, temporal consistency, robustness, and planning-oriented assessment. Finally, we discuss open challenges and future directions toward unified infrastructure representation, open-environment generalization, relation- and rule-aware reasoning, and downstream-oriented evaluation. By connecting tasks, representations, and evaluation under a common functional framework, this survey aims to establish road infrastructure perception as a coherent foundation for map-compatible and behavior-relevant autonomous-driving scene understanding.