In the autonomous driving field, the fusion of human knowledge into Deep Reinforcement Learning (DRL) is often based on the human demonstration recorded in the simulated environment. This limits the generalization and the feasibility of application in real-world traffic. We proposed a two-stage DRL method, that learns from real-world human driving to achieve performance that is superior to the pure DRL agent. Training a DRL agent is done within a framework for CARLA with Robot Operating System (ROS). For evaluation, we designed different real-world driving scenarios to compare the proposed two-stage DRL agent with the pure DRL agent. After extracting the 'good' behavior from the human driver, such as anticipation in a signalized intersection, the agent becomes more efficient and drives safer, which makes this autonomous agent more adapt to Human-Robot Interaction (HRI) traffic.

翻译：在自主驾驶领域,将人类知识融入深强化学习(DRL)往往以模拟环境中记录的人类演示为基础,这限制了在现实世界交通中应用人类知识的普及性和可行性。我们提出了一个两阶段DRL方法,从现实世界人类驾驶中学习,以达到优于纯DRL剂的性能。在使用机器人操作系统(ROS)的CARLA框架内培训DRL代理。在评估方面,我们设计了不同的现实世界驾驶方案,将拟议的两阶段DRL剂与纯DRL剂进行比较。在从人驾驶器中提取“良好”行为(例如信号化十字路口的预言)之后,该代理效率更高,驱动器更安全,从而使该自主代理更能适应人类机器人互动(HRI)的交通。