HLSR: Hybrid Live-Forecast Selective Dynamic Vehicle Rerouting for Real-Time Congestion Avoidance
Traffic congestion in urban areas hampers productivity, elevates travel expenses, and contributes to increased emissions. Current rerouting methods typically assume that all vehicles will be redirected, which is not feasible. This paper introduces HLSR, a selective hybrid live-forecast vehicle rerouting system that integrates real-time edge speeds with short-term forecasts while allowing for limited intervention. Key strategies include dual-threshold congestion detection, calibrated upstream selection, and travel-time predictions customized for drivers. Additionally, HLSR features three elements: approaching-vehicle expansion, travel-time-weighted k-shortest-path creation, and a hybrid live-forecast segment speed that is horizon-dependent for multi-cost route distribution. This innovative speed metric improves adaptive routing choices. The paper falls under Computer Science > Artificial Intelligence and is accessible as an arXiv preprint, pertinent to intelligent transportation systems and AI-based traffic management.
Key facts
- HLSR is a selective hybrid live-forecast vehicle rerouting framework for congestion avoidance.
- It fuses live edge speeds with short-horizon forecasts under a limited intervention scope.
- The framework uses dual-threshold congestion detection.
- It includes calibrated upstream selection of road segments.
- Driver-tailored travel-time prediction is a core component.
- Approaching-vehicle expansion is introduced to account for vehicles moving toward congestion.
- Travel-time-weighted k-shortest-path generation and a horizon-dependent hybrid speed metric are novel additions.
- The paper is categorized under Computer Science > Artificial Intelligence on arXiv.
Entities
—