Agent-Based Game Theory Modeling for Driverless Vehicles at Intersections

Rakha, Hesham A.; Zohdy, Ismail H.; Kamalanathsharma, Raj K. · 2013 · ROSA P / United States. Dept. of Transportation. Research and Innovative Technology Administration

archive: archived pipeline: cataloged verified

Get this paper ↗ (full text — opens at the source; we link to it, we don't host it)

Summary

This report presents three research efforts focused on agent-based game theory modeling for driverless and automated vehicles at intersections, aiming to improve traffic efficiency and safety through advanced control strategies. The first effort develops a reactive-driving agent-based algorithm to model driver left-turn gap acceptance behavior at signalized intersections. This model integrates driver characteristics, psychological deliberation, and vehicle physical capabilities via a vehicle dynamics model. It was calibrated using 301 accepted gaps and validated against 2,429 rejected gaps at the same site, as well as 1,485 gap decisions at a different site. The agent-based model, which estimates a driver-specific critical gap by comparing offered gaps against calculated thresholds, achieved 90% prediction accuracy. It outperformed standard logistic regression models in consistency and transferability, providing a foundational framework for modeling autonomous vehicle decision-making. The second effort proposes a heuristic optimization algorithm for automated vehicles equipped with Cooperative Adaptive Cruise Control (CACC) systems at uncontrolled intersections. Using a game theory framework, the system models automated vehicles as reactive agents collaborating with an intersection controller to minimize total delay. The system was evaluated through Monte Carlo simulations repeated 1,000 times, comparing a traditional four-way stop control against the proposed controller framework. Results indicated that the proposed system reduced total delay by an average of 35 seconds, representing approximately a 70% reduction compared to traditional stop controls. The third effort introduces iCACC, a tool for optimizing autonomous vehicle movements through intersections by controlling trajectories via CACC systems to prevent collisions and minimize delay. Simulations compared conventional signal control with iCACC, measuring delay and fuel consumption. The iCACC system demonstrated savings of 91% in delay and 82% in fuel consumption relative to conventional signal control. Collectively, these findings suggest that agent-based modeling and cooperative control strategies significantly enhance intersection efficiency, reduce fuel usage, and provide essential groundwork for the development of connected and autonomous vehicle applications.

Key finding

The proposed agent-based gap acceptance model achieved 90% correct predictions, while the game theory-based intersection control system reduced total delay by approximately 70 percent and iCACC reduced delay and fuel consumption by 91 and 82 percent, respectively, compared to conventional control methods.

Methodology

mixed_methods

Sample size: 2730

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed. Discovered via bulk_ingest_rosap on 2026-05-23 (6 acquisition events logged).

Summary generated by qwen3.6-27b-prismaquant on 2026-06-10; verification: verified_with_issues.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• gap acceptance
• mental model of traffic

Information type

What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).

• Theoretical Contribution: computational model