Interdisciplinary

Smart Traffic Systems Help Autonomous Vehicle Groups Navigate Intersections Efficiently

AI Insight

Researchers developed a speed guidance strategy for connected and autonomous vehicles (CAVs) at signalized intersections that recognizes vehicle platoons and provides tailored guidance (acceleration, deceleration, or platoon splitting) based on traffic conditions. Testing through traffic simulation showed the strategy reduced fuel consumption by up to 40%, delay time by 37%, and vehicle stops by 23% compared to no guidance, with benefits becoming most pronounced when CAV penetration rates reached 70%. The system accounts for different CAV penetration rates, clustering patterns, and mixed traffic scenarios to optimize platoon passage through intersections.


This research provides a practical framework for reducing urban traffic congestion and energy consumption as autonomous vehicles become more prevalent on roads. The findings suggest significant environmental and efficiency benefits can be achieved even before full autonomous vehicle adoption, with meaningful improvements starting at 70% CAV penetration.


Understand the Science

Autonomous vehicle Concept coming soon Platoon (automobile) Concept coming soon Traffic light Concept coming soon

by Shenzhen Ding, Zhengjun Wu, Fei Peng, Yanwei Xu, Xin Wang, Aihua Fan, Rongjun Zheng

To alleviate the issues of widespread traffic congestion and low passage efficiency at urban signalised intersections, which result in increased vehicle energy consumption, this paper proposes a speed guidance strategy based on platoon recognition in connected and autonomous vehicle (CAV) environments. The study focuses on vehicle platoons, considering the impact of varying CAV penetration rates, CAV aggregation intensity and the spatio-temporal distribution of mixed traffic flows. Six distinct platoon passage scenarios through intersections are defined, based on whether platoons encounter obstructions. Three distinct guidance strategies are proposed for these scenarios: acceleration guidance, deceleration guidance and platoon splitting. Finally, a case study on secondary development based on Vissim is conducted. The results show that the platoon-based speed guidance strategy reduces vehicle fuel consumption (from 3.152 to 0.600 L/s), delay time (from 9.22 to 3.79 s), and the number of stops (from 0.18 to 0.04 times) compared to no speed guidance Furthermore, the effectiveness of platoon-based speed guidance strategies varies with CAV penetration rates. As the CAV penetration rate approaches 0.7, the benefits to traffic of the guidance strategy become more apparent. The most significant reductions were observed in fuel consumption, delay time and the number of stops: 40%, 37% and 23%.

Source: Speed guidance strategy at intersections based on platoon recognition in connected and autonomous vehicles environments