Dynamic driving and routing games for autonomous vehicles on networks: A mean field game approach

TL;DR

This paper introduces a mean field game approach to optimize autonomous vehicles' velocity and route choices on networks, addressing limitations of traditional dynamic traffic assignment models by explicitly modeling velocity control.

Contribution

It develops a novel game-theoretic model for AV decision-making, incorporating velocity control and route choice within a mean field game framework, with an efficient solution algorithm.

Findings

Lower travel costs achieved with the proposed model on test networks

Braess paradox can still occur under certain conditions

Efficient algorithm successfully solves the complex game structure

Abstract

This paper aims to answer the research question as to optimal design of decision-making processes for autonomous vehicles (AVs), including dynamical selection of driving velocity and route choices on a transportation network. Dynamic traffic assignment (DTA) has been widely used to model travelers's route choice or/and departure-time choice and predict dynamic traffic flow evolution in the short term. However, the existing DTA models do not explicitly describe one's selection of driving velocity on a road link. Driving velocity choice may not be crucial for modeling the movement of human drivers but it is a must-have control to maneuver AVs. In this paper, we aim to develop a game-theoretic model to solve for AVs's optimal driving strategies of velocity control in the interior of a road link and route choice at a junction node. To this end, we will first reinterpret the DTA problem as an N-car differential game and show that this game can be tackled with a general mean field game-theoretic framework. The developed mean field game is challenging to solve because of the forward and backward structure for velocity control and the complementarity conditions for route choice. An efficient algorithm is developed to address these challenges. The model and the algorithm are illustrated on the Braess network and the OW network with a single destination. On the Braess network, we first compare the LWR based DTA model with the proposed game and find that the driving and routing control navigates AVs with overall lower costs. We then compare the total travel cost without and with the middle link and find that the Braess paradox may still arise under certain conditions. We also test our proposed model and solution algorithm on the OW network.