Game-Theoretic Modeling of Multi-Vehicle Interactions at Uncontrolled Intersections

Motivated by the need for simulation tools testing, verification and validation of autonomous driving systems that operate in traffic consisting both human-driven vehicles, we propose a game-theoretic framework modeling interactive behavior vehicles at uncontrolled intersections. The proposed vehicle interaction model is based on novel formulation dynamic games with multiple concurrent leader-follower pairs, induced from common rules. Based results various intersection scenarios, show exhibits reasonable expected traffic, including capability reproducing scenarios extracted real-world data performance resolving conflicts. further validated level-of-service quality rating system demonstrates manageable computational complexity compared to traditional multi-player models.