Integrating adaptive signal control and autonomous vehicles for urban congestion relief and carbon reduction

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

🔬研究者:Methodology combining micro-simulation, emission models, and interpretable ML offers a replicable framework for urban transport decarbonization studies.

🏢実務担当者:Demonstrates that coordinated AV-ATSC deployment can reduce fuel costs and emissions, with cost-benefit ratios favoring moderate-infrastructure cities.

🏛政策担当者:Quantifies the economic and environmental case for integrating AV policy with adaptive traffic management as a cost-effective decarbonization pathway.

<title>Abstract</title> <p> Adaptive traffic signal control (ATSC) and autonomous vehicles (AVs) are widely recognized for their potential to reduce traffic congestion and associated carbon emissions ^1–3 , however their coordinated system-level impacts, cross-city variability, and economic feasibility remain poorly understood. In this study, we develop a city-scale evaluation framework that integrates microscopic traffic simulation, vehicle-level emission estimation, and interpretable machine learning. We apply this framework to both a real-world urban corridor and 100 major cities in China. In a representative urban corridor, coordinated deployment significantly outperforms single-technology strategies, reducing average travel time by approximately 32% and per-vehicle CO₂ emissions by about 36%. These improvements do not result from simple technological superposition but from a systemic reconfiguration of vehicle operating states that reduces stop-and-go behavior, suppresses high-delay and high-emission operating regimes, and enhances traffic flow continuity. Extending the analysis to 100 cities further reveals substantial heterogeneity in these benefits. The coordinated strategy increases travel speeds by at least 20% and reduces emissions by more than 10%, with greater operational gains observed in cities with relatively dense road networks and unsaturated traffic conditions. High benefit–cost ratios are more likely to emerge in cities with moderate infrastructure supply and stronger economic value. Economically, the strategy generates approximately 7 million hours of annual travel-time savings, equivalent to nearly US$70 billion in time-value benefits, alongside approximately US$46.1 billion in environmental benefits and US$50.6 billion in fuel savings annually. These findings demonstrate that coordinated infrastructure–vehicle intelligence can deliver large-scale congestion mitigation and decarbonization without relying on continued road expansion, offering a new pathway for low-carbon urban transitions and next-generation smart-city governance. </p>

• Research Square https://doi.org/10.21203/rs.3.rs-9996386/v1first seen 2026-07-03 04:26:00