In this paper, we model a decision-making process involving a set of interacting agents. We use Markovian opinion dynamics, where each agent switches between decisions according to a continuous time Markov chain. Existing opinion dynamics models are extended by introducing attractive and repulsive forces that act within and between groups of agents, respectively. Such an extension enables the resemblance of behaviours emerging in networks where agents make decisions that depend both on their own preferences and the decisions of specific groups of surrounding agents. The considered modeling problem and the contributions in this paper are inspired by the interaction among road users (RUs) at traffic junctions, where each RU has to decide whether to go or to yield.

In this paper, we model a decision making process in a network of interacting agents using Markovian opinion dynamics, where each agent switches between decisions according to a continuous time Markov chain. We are inspired by the problem of modeling how interaction among road users in a traffic intersection affects the choice that each agent makes concerning where to exit and whether or not to give way. We introduce attractive/repulsive forces that act within and between groups of agents, with the objective of resembling the behaviors emerging in networks where agents make decisions that depend both on their own preferences and the decisions of the surrounding agents. Our model extends the possibility of using Markovian opinion dynamics to describe a wider scope of practical scenarios, in which groups of stochastic agents make collective decisions. In traffic applications, our method could be used in autonomous vehicles to predict the decisions of human road users.