To simulate pedestrian crowds, most of the current studies use the microscopic approach, in which the pedestrian is modeled as an individual entity. With the microscopic approach, the heterogeneity in the pedestrian population is mostly based on inter-individual difference in the agent model parameters, like speed, destination, etc. In fact, what can be seen in congested real situations, is some pedestrians choosing to temporarily follow other ones in order to facilitate the flow while going on avoiding collisions. Each pedestrian can choose to adopt and leave such a behavior according to his/her individual and local situation. In order to model and simulate this behavior, we propose to include in the pedestrian agent navigational model a decision process that allows to activate the following task in addition to the collision avoidance task. The decision depends on the agent’s internal state and on what it perceives in its environment. Our proposition is an attempt to define the conditions that must trigger the switching to another navigation mode, and the selection of the other agent to be followed, i.e. the 'leader'.
