A Congestion Mitigation Approach For Ground Vehicles With Diverse Advanced Driver Assistance Systems In Smart Transportation Networks
Abstract
Traffic congestion is a frustrating, costly, and persistent problem in transportation networks throughout the world. Expectations that the advent of increasingly autonomous vehicles will enable centralized, network-optimal routing to mitigate congestion have failed to come to fruition, with selfish driving tendencies taking precedence despite vehicles increasingly being equipped with diverse advanced driver assistance systems (ADAS) enabling varying levels of vehicular autonomy. Proposed congestion mitigation approaches largely consider vehicles as static agents that are fully human-driven or autonomous, yielding solutions that are incompatible with modern vehicles. To address this, this paper models the interaction between a smart traffic arbitration system (STAS) and a vehicle with multiple distinct ADAS modes as a repeated Stackelberg game with asymmetric information. A regret matching-based Trust-Aware Control Trading Strategy (TACTS) is proposed to dynamically update the STAS's mixed strategy over which mode should be in control of the vehicle at each vertex in a route. Theoretical results provide bounds on the realized network-wide travel time under TACTS relative to the optimal network-wide travel time. Experimental results of traffic simulations in several real-world networks under various congestion levels demonstrate that TACTS consistently reduces network-wide congestion and outperforms alternative routing and control allocation strategies, reducing network wide travel time by at least 4.2% on average in comparison.
Recommended Citation
D. E. Brown and S. K. Das, "A Congestion Mitigation Approach For Ground Vehicles With Diverse Advanced Driver Assistance Systems In Smart Transportation Networks," Proceedings 2026 IEEE International Conference on Smart Computing Smartcomp 2026, pp. 128 - 135, Institute of Electrical and Electronics Engineers, Jan 2026.
The definitive version is available at https://doi.org/10.1109/SmartComp69968.2026.00028
Department(s)
Computer Science
Keywords and Phrases
Advanced Driver Assistance System; Congestion Mitigation; Selfish Routing; Smart Transportation Network; Stackelberg Game; Trust
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2026 Institute of Electrical and Electronics Engineers, All rights reserved.
Publication Date
01 Jan 2026
Comments
National Science Foundation, Grant ECCS-2319995