As a critical component of the vehicle-road-cloud system, high-definition (HD) maps not only provide essential auxiliary information to intelligent connected vehicles but also serve as a unified spatiotemporal reference between vehicles and intelligent roadside infrastructure. However, existing HD maps primarily focus on static road information, with limited representation of dynamic data. Given the rapidly changing road environments, the diversity and heterogeneity of road information, and the significant uncertainties, static data alone cannot fully depict a comprehensive and accurate driving environment. To address these challenges, this study proposes a dynamic cognitive map specifically designed for vehicle-road-cloud systems. The study begins by exploring the definition and framework of dynamic cognitive maps, followed by the development of a logical model inspired by the spatial cognition mechanisms of brain. Lastly, this paper introduces and analyzes the key technologies of dynamic cognitive maps. The proposed dynamic cognitive map aims to advance the practical implementation and application of intelligent connected vehicles.