Driving Conflict Resolution of Autonomous Vehicles at Unsignalized Intersections: A Differential Game Approach

TL;DR

This paper introduces a differential game-based decision-making framework for autonomous vehicles at unsignalized intersections, incorporating personalized driving preferences, safety assessment, and real-time implementation validation.

Contribution

It develops a novel decision-making approach that integrates personalized aggressiveness, collision risk modeling, and equilibrium solutions for autonomous vehicle conflict resolution.

Findings

The framework achieves real-time decision-making in hardware-in-the-loop tests.

It effectively balances safety and efficiency in autonomous driving scenarios.

Both Nash and Stackelberg equilibria are feasible solutions for conflict resolution.

Abstract

Considering personalized driving preferences, a new decision-making framework is developed using a differential game approach to resolve the driving conflicts of autonomous vehicles (AVs) at unsignalized intersections. To realize human-like driving and personalized decision-making, driving aggressiveness is first defined for AVs. To improve driving safety, a Gaussian potential field model is built for collision risk assessment. Besides, in the proposed decision making framework, the collision risk assessment model is further used to reduce the computational complexity based on an event-triggered mechanism. In the construction of payoff function, both driving safety and passing efficiency are comprehensively considered, and the driving aggressiveness is also reflected. Two kinds of equilibrium solution to the differential game, i.e., the Nash equilibrium and Stackelberg equilibrium, are discussed and solved. Finally, the proposed decision making algorithm is tested through a hardware-in-the-loop testing platform, and its feasibility, effectiveness and real-time implementation performance are validated.