Agent-based model shows how self-driving cars improve ramp traffic flow
Agent-Based Evolutionary Dynamics for Mixed Autonomy Weaving Ramps
Multiagent Systems
Summary
Traffic involving both human-driven and self-driving cars can be hard to understand, especially when these cars try to help each other. The authors created a detailed computer model where each car decides its lane based on simple rules inspired by kindness toward others. They proved that these decisions lead the whole traffic system to a steady balance, matching what bigger traffic theories predict. Their model also shows how differences between cars and imperfect knowledge affect traffic and cooperation over time.
What this means in practice
- •For traffic system planners: Design and test lane management policies for ramps with mixed automated and human-driving vehicles using adaptive behaviors.
- •For autonomous vehicle software developers: Incorporate decentralized lane-switching strategies that balance individual and collective traffic benefits in mixed autonomy driving scenarios.
Authors
Sheryl Paul, Kexin Wang, Ruolin Li, Jyotirmoy V. Deshmukh
Abstract
Existing models of mixed-autonomy weaving ramps characterize how altruistic connected and automated vehicles (CAVs) can improve traffic efficiency at the population level, but provide limited insight into how such behavior emerges from decentralized vehicle interactions or how it is affected by finite populations, heterogeneous preferences, and imperfect information. We develop an agent-based model of a macroscopic weaving-ramp framework in which individual vehicles adapt their lane choices using an evolutionary game-theoretic update rule and altruism-based objectives providing a microscopic interpretation of the original Wardrop model. We prove convergence of the decentralized dynamics to the unique equilibrium predicted by the macroscopic theory. Beyond reproducing aggregate equilibrium behavior, the framework enables the study of deployment-level questions that cannot be addressed by static analysis. Simulation results demonstrate close agreement with the macroscopic predictions while revealing how convergence rates, adaptation to changing traffic conditions, heterogeneous altruism levels among CAVs, and imperfect state information influence system performance and the distribution of altruistic burden across vehicles. These results provide a bridge between equilibrium traffic theory and decentralized mixed-autonomy deployment.