HLSR: Hybrid Live Forecast Selective Dynamic Vehicle Rerouting for Real-Time Congestion Avoidance
2026-08-18 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors present HLSR, a method to reduce traffic jams by selectively rerouting certain vehicles instead of all of them, using a mix of current road speeds and short-term forecasts. Their approach detects congestion with specific thresholds and predicts travel times tailored to drivers. It also considers vehicles approaching congested areas and plans routes based on multiple path options weighted by travel time. This technique aims to improve rerouting efficiency without needing to replan routes for every vehicle constantly.
urban traffic congestionlive travel-time reroutingshort-horizon forecastingcongestion detectiontravel-time predictionk-shortest-pathmulti-cost route allocationtraffic simulationvehicle rerouting
Authors
Xiao Wang, Shun Ren Yang, Hui Nien Hung
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.