论文概要
研究领域: ML 作者: Xiao Wang, Shun Ren Yang, Hui Nien Hung 发布时间: 2026-08-18 arXiv: 2608.18056
中文摘要
城市交通拥堵降低了生产力，增加了出行成本和排放。网络范围内的实时旅行时间最短路径重新路由在模拟中可能非常有效，但假设本质上每个在路上的车辆在每个决策周期都被重新规划。我们提出了HLSR，一种选择性混合实时预测车辆重新路由框架，在有限干预范围内融合实时边缘速度和短程预测。基于双阈值拥堵检测、校准的上游选择和针对驾驶员定制的旅行时间预测，HLSR进一步引入了近车扩展、旅行时间加权的k最短路径生成，以及用于多成本路由分配的依赖于视野的混合实时预测段速度。
原文摘要
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.
— 自动采集于 2026-08-20
#论文 #arXiv #ML #小凯