← 研踪 PaperTrailarXiv:2611.15774 · v1
Coverage-Aware Routing with Approximate Equilibrium Guarantees for Location-Diversity Vehicular Crowdsensing
首次提交 2026-11-12 01:51
版本更新 2026-11-12 01:51
雷达观测 2026-11-13 14:16
摘要
Vehicular crowdsensing uses the sensors of everyday vehicles to monitor cities, but traffic concentrates on few roads, leaving much of the network unsensed. Location-diversity incentives pay vehicles more to travel where few others go, but our earlier mechanism sets how far each vehicle deviates without optimizing collective coverage in route selection. We add this step in two stages. First, a non-cooperative game with diversity-weighted rewards yields each vehicle's equilibrium deviation. Second, the platform recommends to each vehicle a feasible route whose deviation is within a tolerance of this value, chosen to improve coverage. The coverage gain is monotone submodular, so a greedy router with local search attains at least half of the optimal gain over generated candidates. If every active vehicle has a candidate within a tolerance that is small relative to the aggregate deviation, the recommended routes form an -Nash equilibrium, with first order in the tolerance, or second order under a stronger condition. On London and Monaco road networks, the router achieves 99.4% and 98.9% of the optimal reduction in the coverage penalty on small instances and exceeds closest-length selection by up to 27.9 points. Under heterogeneous costs, uniform deviation needs compensation averaging 42% of the budget to give every vehicle nonnegative utility; the equilibrium targets need almost none. They also yield more coverage per unit of added travel in most settings and up to 22.6 more points at small budgets, an advantage that depends on placement and reverses at large budgets, where detour limits bind.
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-12 01:51 · 最新观测版本
Coverage-Aware Routing with Approximate Equilibrium Guarantees for Location-Diversity Vehicular Crowdsensing
Vehicular crowdsensing uses the sensors of everyday vehicles to monitor cities, but traffic concentrates on few roads, leaving much of the network unsensed. Location-diversity incentives pay vehicles more to travel where few others go, but our earlier mechanism sets how far each vehicle deviates without optimizing collective coverage in route selection. We add this step in two stages. First, a non-cooperative game with diversity-weighted rewards yields each vehicle's equilibrium deviation. Second, the platform recommends to each vehicle a feasible route whose deviation is within a tolerance of this value, chosen to improve coverage. The coverage gain is monotone submodular, so a greedy router with local search attains at least half of the optimal gain over generated candidates. If every active vehicle has a candidate within a tolerance that is small relative to the aggregate deviation, the recommended routes form an -Nash equilibrium, with first order in the tolerance, or second order under a stronger condition. On London and Monaco road networks, the router achieves 99.4% and 98.9% of the optimal reduction in the coverage penalty on small instances and exceeds closest-length selection by up to 27.9 points. Under heterogeneous costs, uniform deviation needs compensation averaging 42% of the budget to give every vehicle nonnegative utility; the equilibrium targets need almost none. They also yield more coverage per unit of added travel in most settings and up to 22.6 more points at small budgets, an advantage that depends on placement and reverses at large budgets, where detour limits bind.
查看此版本解读 →查看此版本原文 ↗