A Dual-User High-Definition Map Information Transmission Model Based on Temporal Evolution

Objectives: Existing high-definition (HD) map information transmission models fail to distinguish between machine and human users and lack adequate expression of cross-cycle feedback mechanisms, making them inadequate for scenarios requiring high-frequency updates and diverse application contexts in autonomous driving. This study aims to construct a specialized transmission model tailored to HD maps that addresses these limitations by explicitly integrating dual-user requirements and temporal evolutionary characteristics.Methods: This research introduces a temporal dimension to transform the traditional planar closed-loop structure into a stereoscopic circulation architecture, proposing a dual-user HD map information transmission model based on temporal evolution. The methodological framework encompasses three key innovations:(1) Structural Extension and Dual-User Integration: The model explicitly distinguishes machine users (autonomous driving systems) and human users (passengers and operators), establishing a coordinated transmission mechanism. Machine users directly access structured semantic data in HD maps for perception, decision-making, and actuation, while human users rely on visualized high-fidelity maps for intuitive symbolic representations. This architecture enables clear separation of personalized information flows—mapping passenger needs (route preferences, comfort requirements) and vehicle data (sensor precision, dynamic performance) to respective user entities. The transmission operates through parallel loops: cartographers encode the real world into semantic HD maps delivered to machine users (primary loop) while simultaneously rendering visualized maps for passengers (secondary loop), with both user types providing feedback to cartographers.(2) Compositional Fusion of Visual and Semantic Paradigms: The model integrates the Kolácný visual map model with HD semantic map transmission systems through dual-channel architecture. This fusion combines visual symbols (for human interpretation) with digital semantics (for machine processing), establishing bidirectional mapping where semantics correspond to standardized symbols. HD maps maintain pure semantic data for machine consumption, while visualized HD maps convert semantic data into graphic symbol systems for human cognition. This design accommodates autonomous driving reality where machines require direct semantic access without decoding overhead, while passengers need symbolic visualization for comprehension and trust-building.(3) Dimensional Enhancement Through Temporal Serialization: The model introduces temporal dimensionality operating at two scales. Within cycles: traditional planar models superimpose temporally distinct versions onto single nodes; the model separates map versions (cartographer's at completion, user's at initiation) and real-world versions through sequential serialization, inscribing temporal positions on a vertical axis. This enables explicit expression of feedback mechanisms including personalized demands and effectiveness evaluations. Between cycles: the model transforms planar closed loops into spiral iterative structures where sequential cycles connect end-to-end. Each cycle carries complete transmission (real world → cartographer reality → HD map → user reality → real world), with adjacent cycles linking through cross-cycle feedback. This reconstructs reverse paths in traditional models as forward processes across cycles (User (Cycle n) → Personalized Information → Cartographer (Cycle n+1)), eliminating temporal ambiguity while supporting high-frequency updates required for real-time traffic scenario adaptation.Results: Comparative analysis demonstrates that the dual-user model achieves significant evolutionary advances across multiple dimensions relative to single-user models. Structurally, it implements a machine-human collaborative transmission mechanism that simultaneously serves autonomous vehicle decision-making (through structured semantic HD maps) and passenger experience (through visualized high-fidelity maps). Compositionally, it successfully fuses the Kolácný visual paradigm with HD semantic map transmission systems, enabling dual-channel information flow: semantic data for direct machine processing and symbolic representations for intuitive human comprehension. Dimensionally, temporal enhancement transforms spatial reverse loops into spatiotemporal forward progressions, explicitly expressing cross-cycle feedback from "User Reality (Cycle n)" to "Cartographer Reality (Cycle n+1)" while eliminating temporal ambiguity inherent in planar models. This architectural transformation significantly improves model adaptability to heterogeneous user requirements, enhances information transmission integrity, and strengthens logical clarity and structural interpretability.Conclusions: The proposed dual-user model provides a systematic theoretical framework for analyzing and optimizing HD map information transmission efficiency in autonomous driving contexts. By explicitly coordinating machine and human user requirements through temporal serial communication paradigms, the model substantially enhances system interpretability and readability. The framework offers theoretical foundations for revealing transmission mechanisms, improving update efficiency under high-frequency iteration demands, and supporting the construction of next-generation intelligent transportation map systems. Future research will focus on deepening connotation interpretation of model nodes and edges, refining conversion strategies between HD maps and their visualized derivatives, and strengthening practical alignment with real-world autonomous driving scenarios to establish robust theory-application mapping mechanisms.