Automated Traffic Light Allocation Using Vehicle Trajectories

The system uses feedback from detected vehicle trajectories to automatically allocate traffic lights to traffic lanes. Vehicles detect their own trajectories and trajectories of other vehicles at intersections, transmit this data to a server, and the server uses the accumulated trajectory information to automatically determine which traffic light controls which traffic lane, eliminating manual allocation while maintaining accuracy through data-driven decisions

The system enables self-service by allowing vehicles to automatically detect and report their trajectories and the traffic light states they encounter. Each vehicle independently contributes to the collective data set that enables automatic traffic light allocation, with the server synthesizing this self-reported information to create accurate allocations without human intervention

The system introduces vehicle trajectories as an intermediary element to replace direct reliance on road markings. Instead of using directional arrows painted on the road, the system uses the actual paths taken by vehicles (detected by sensors) as the basis for allocation. This intermediary approach maintains reliability because vehicle trajectories are continuously observable and do not depend on the physical condition of road markings

The system replaces the mechanical/visual system of road markings with an electronic/sensor-based system. Rather than relying on painted directional arrows that can be worn or covered, the system uses sensors (cameras, LIDAR) to detect vehicle positions and trajectories, substituting a fragile visual indicator with a robust electronic detection mechanism

The system segments the data collection and processing tasks across multiple independent vehicles and a centralized server. Each vehicle independently detects trajectories and transmits data, while the server segments the processing work by accumulating data from multiple sources and synthesizing it into updated traffic light models. This segmentation enables parallel data collection that improves productivity without requiring any single vehicle to handle the full complexity

The system achieves universality by creating a multi-functional platform where vehicles serve multiple purposes: they detect their own trajectories, detect trajectories of other vehicles, detect traffic light states, and transmit all this data to the server. This universal approach allows the same infrastructure to collect comprehensive data from multiple sources, improving productivity through data aggregation while distributing the processing complexity across the network