🤖 AI Summary
Conventional vehicle-centric intelligence and human driving struggle to perceive surrounding vehicles’ intentions and infrastructure states in real time and with sufficient accuracy—particularly in complex scenarios such as lane merging—leading to safety hazards and constrained traffic efficiency.
Method: This paper proposes a vehicle–infrastructure–cloud cooperative paradigm for real-time intention and state sharing, establishing a spatiotemporal global traffic awareness framework that overcomes the limitations of isolated perception. It integrates heterogeneous multi-source data, leverages ultra-low-latency V2X communication, employs dynamic spatiotemporal modeling, and coordinates edge–cloud computing for system-level situational understanding.
Contribution/Results: Experiments demonstrate a significant reduction in collision rates within merging zones, a >15% improvement in segment-level traffic capacity, and support for real-time traffic态势 prediction and proactive traffic management decision-making.
📝 Abstract
Traditional manual driving and single-vehicle-based intelligent driving have limitations in real-time and accurate acquisition of the current driving status and intentions of surrounding vehicles, leading to vehicles typically maintaining appropriate safe distances from each other. Yet, accidents still frequently occur, especially in merging areas; meanwhile, it is difficult to comprehensively obtain the conditions of road infrastructure. These limitations not only restrict the further improvement of road capacity but also result in irreparable losses of life and property. To overcome this bottleneck, this paper constructs a space-time global view of the road traffic system based on a real-time sharing mechanism, enabling both road users and managers to timely access the driving intentions of nearby vehicles and the real-time status of road infrastructure.