基于代理的建模（ABM）是一种建模，以调查和预测通过模拟在给定场景中的自主代理中的大型自主代理的动作和相互作用来实现复杂组行为的出现。ABM已广泛用于学术界，例如博弈论，复杂系统和计算社会学。关于自主驾驶，ABM也是一种流行的模拟方法，例如，在开发驾驶政策和安全验证方面。The conventional motion planning and control methods, e.g., PID control, feedback linearization or model predictive control, expect a prediction over the future trajectories of other traffic participants in order to avoid collisions, but real traffic scenarios involve complex interactions among various road users (Schwarting, Planning and Decision-Making for Autonomous Vehicles, MIT, 2018). To conquer this challenge, the emerging trends are the behavior-aware motion planning and learning-based approaches. ABM is then could be naturally exploited to handle the complex, cluttered environments while modeling the uncertain interactions with each other. This would expend Simulink as an integrated platform to develop and verify learning-based algorithms. For a description, you can see this video:https://www.youtube.com/watch?v=nKOleGGEwJI