Vehicle-Road-Cloud Collaborative Perception Framework and Key Technologies: A Review
Bolin Gao, Jiaxi Liu, Hengduo Zou, Jiaxing Chen, Lei He, Keqiang Li
Abstract
Over recent years, the Vehicle-Road-Cloud Integration System (VRCIS) and Intelligent and Connected Vehicles (ICVs) have gained significant attention in the realm of autonomous driving. By sharing data across diverse traffic participants and coordinating with VRCIS, ICVs can achieve enhanced perception accuracy and superior driving decisions, surpassing autonomous vehicles that rely solely on onboard sensors. Existing literature explores VRCIS’ overall architecture, applications, and deployment status. However, there is a lack of a comprehensive review focusing on the overarching architecture of ICV’s perception and its associated technologies, which are fundamental to VRCIS from an information integration perspective. This gap hinders the development of a robust perception framework for VRCIS, including the crucial perception technologies specific to it. This survey seeks to bridge this gap by offering an exhaustive review of the designed VRCIS perception framework and its specific perception technologies. Firstly, an overview of VRCIS’ perception architecture is provided, and the application relationships among various perception technologies are elucidated. Then, single-node, multi-node, and vehicle-road-cloud collaborative perception technologies are explored in sequence. Finally, the survey concludes with a discussion of insights and prospective future directions for VRCIS.