The integration of Autonomous Vehicles (AVs) into existing human-driven traffic systems poses considerable challenges, especially within environments where human and machine interactions are frequent and complex, such as at unsignalized intersections. Addressing these challenges, we introduce a novel framework predicated on dynamic and socially-aware decision-making game theory to augment the social decision-making prowess of AVs in mixed driving environments.This comprehensive framework is delineated into three primary modules: Social Tendency Recognition, Mixed-Strategy Game Modeling, and Expert Mode Learning. We introduce 'Interaction Orientation' as a metric to evaluate the social decision-making tendencies of various agents, incorporating both environmental factors and trajectory data. The mixed-strategy game model developed as part of this framework considers the evolution of future traffic scenarios and includes a utility function that balances safety, operational efficiency, and the unpredictability of environmental conditions. To adapt to real-world driving complexities, our framework utilizes dynamic optimization techniques for assimilating and learning from expert human driving strategies. These strategies are compiled into a comprehensive library, serving as a reference for future decision-making processes. Our approach is validated through extensive driving datasets, and the results demonstrate marked enhancements in decision timing, precision.

翻译：将自动驾驶车辆（AVs）融入现有的人类驾驶交通系统面临巨大挑战，特别是在无信号交叉口等人类与机器交互频繁且复杂的场景中。为解决这些挑战，我们提出了一种基于动态社会感知决策博弈论的新型框架，以提升自动驾驶车辆在混合驾驶环境中的社会性决策能力。该综合框架由三个主要模块组成：社会倾向识别、混合策略博弈建模和专家模式学习。我们引入"交互倾向"作为评估各智能体社会性决策倾向的指标，综合考虑环境因素与轨迹数据。作为该框架组成部分的混合策略博弈模型，不仅考虑了未来交通场景的演化，还构建了平衡安全性、运行效率与环境条件不可预测性的效用函数。为适应真实驾驶环境的复杂性，我们采用动态优化技术吸收学习人类专家驾驶策略，并将这些策略编译成综合数据库，作为未来决策过程的参考依据。通过大规模驾驶数据集验证，实验结果表明该方法在决策时机和精确性方面均取得显著提升。