Landmarks have been identified as relevant and prominent urban elements, explicitly involved in human navigation processes. Despite the understanding accumulated around their functions, landmarks have not been included in simulation models of pedestrian movement in urban environments. In this paper, we describe an Agent-Based Model (ABM) for pedestrian movement simulation that incorporates the role of on-route and distant landmarks in agents' route choice behaviour. Route choice models with and without landmarks were compared by using four scenarios: road distance minimisation, least cumulative angular change, road distance minimisation and landmarks, least cumulative angular change and landmarks. The city centre of London was used as a case study and a set of GPS trajectories was employed to evaluate the model. The introduction of landmarks led to more heterogeneous patterns that diverge from the minimisation models. Landmark-based navigation brought about high pedestrian volumes along the river (up to 13% of agents) and the boundaries of the parks (around 8% of the agents). Moreover, the model evaluation showed that the results of the landmark-based scenarios were not significantly different from the GPS trajectories in terms of cumulative landmarkness, whereas the other scenarios were. This implies that our proposed landmark-based route choice approach was better able to reproduce human navigation. At the street-segment level, the pedestrian volumes emerging from the scenarios were comparable to the trajectories' volumes in most of the case study area; yet, under- and over-estimation were observed along the banks of the rivers and across green areas (up to +7%, −11% of volumes) in the landmark-based scenarios, and along major roads (up to +11% of volumes) in the least cumulative angular change scenario. While our model could be expanded in relation to the agents' cognitive representation of the environment, e.g. by considering other relevant urban elements and accounting for individual spatial knowledge differences, the inclusion of landmarks in route choice models results in more plausible agents that make use of relevant urban information.

地标已被确定为相关且突出的城市元素，明确涉及人类导航过程。尽管对功能的理解有所积累，但地标尚未纳入城市环境中行人运动的仿真模型中。在本文中，我们描述了一种用于行人运动模拟的基于主体的模型（ABM），该模型结合了沿途和远方地标在主体的路径选择行为中的作用。通过使用以下四种情况对具有和不具有地标的路线选择模型进行了比较：道路距离最小化，最小累积角度变化，道路距离最小化和地标，最小累积角度变化和地标。以伦敦市中心为例，并使用一组GPS轨迹评估模型。地标的引入导致与最小化模型不同的更多异构模式。基于地标的导航导致沿河的行人流量大（最多占代理商的13％）和公园的边界（大约占代理商的8％）。此外，模型评估表明，基于地标的场景的结果在累积地标性方面与GPS轨迹没有显着差异，而其他场景则不同。这意味着我们提出的基于地标的路线选择方法能够更好地重现人类的导航。在街道段一级，场景中出现的行人量可与大多数案例研究区域中的轨迹量相媲美。然而，在以地标为基础的情景中，沿河两岸和整个绿地（最多为容积的+7％，-11％）以及主要道路（最多为容积的+ 11％）观察到了低估和高估）在最小的角度变化情况下。虽然我们的模型可以根据代理人对环境的认知表示进行扩展，例如通过考虑其他相关的城市要素并考虑各个空间知识的差异，但在路线选择模型中包含地标会导致更合理的代理人利用相关的城市信息。