Accurate modeling of bicycles in microsimulation tools is challenging due to the limited availability of detailed data, complexity of cyclist decision-making, and heterogeneity in cycling behavior. This paper proposes an agent-based bicycle simulation method in which generative adversarial imitation learning (GAIL) is used to infer the uncertain intentions and heterogeneous preferences of cyclists from observational data. The model is tested on video-derived data of cyclists on a unidirectional path in Vancouver, Canada. In cross-validation, multivariate distributions of movement variables such as speed, direction, and spacing are similar between observed and simulated cyclist trajectories. The model also performs well in comparison to two other cyclist simulation models from the literature. The proposed approach to agent-based microsimulation is a significant advancement, with continuous, non-linear, and stochastic representation of cyclist states, decisions, and actions. The enhanced consideration of cyclist diversity is necessary for developing bicycle networks for all ages and abilities of riders.

由于详细数据的可用性有限、骑车人决策的复杂性以及骑车行为的异质性，在微观仿真工具中对自行车进行准确建模具有挑战性。本文提出了一种基于代理的自行车模拟方法，其中使用生成对抗模仿学习（GAIL）从观察数据中推断出骑车人的不确定意图和异质偏好。该模型在加拿大温哥华的单向路径上对骑自行车者的视频衍生数据进行了测试。在交叉验证中，运动变量（例如速度、方向和间距）的多元分布在观察到的和模拟的骑行者轨迹之间是相似的。与文献中的其他两个骑自行车者模拟模型相比，该模型也表现良好。所提出的基于代理的微观模拟方法是一项重大进步，具有骑车人状态、决策和动作的连续、非线性和随机表示。加强对骑车人多样性的考虑对于开发适合所有年龄和能力的骑手的自行车网络是必要的。