Research
HLSR: Hybrid Live Forecast Selective Dynamic Vehicle Rerouting for Real-Time Congestion Avoidance
arXiv:2608.18056v1 Announce Type: new Abstract: Urban traffic congestion reduces productivity and increases travel cost and emissions. Network-wide live travel-time shortest-path rerouting can be high
arXiv:2608.18056v1 Announce Type: new Abstract: Urban traffic congestion reduces productivity and increases travel cost and emissions. Network-wide live travel-time shortest-path rerouting can be highly effective in simulation, but assumes that essentially every on-road vehicle is replanned every decision period. We propose HLSR, a selective hybrid live--forecast vehicle rerouting framework that fuses live edge speeds with short-horizon forecasts under limited intervention scope. Building on dual-threshold congestion detection, calibrated upstream selection, and driver-tailored travel-time prediction, HLSR further introduces approaching-vehicle expansion, travel-time-weighted k-shortest-path generation, and a horizon-dependent hybrid live--forecast segment speed used in multi-cost route allocation.
Related
- Metropolis-Scale Resilient and Trustworthy Traffic Flow Inference Using Multi-Source Data
- Dijkstra as an Oracle for Online Stochastic Shortest Path Navigation with Provable Guarantees
- From Mobile Data to Business Insights: An End-to-End Analytics Framework for Large-Scale Urban Mobility Analysis and Decision Support
- Temporal Transfer Learning for Traffic Optimization with Coarse-grained Advisory Autonomy
Source: arXiv cs.AI | 2026-08-19