Game Theory-Based Modeling of Multi-Vehicle/Multi-Pedestrian Interaction at Unsignalized Crosswalks


L. Pavelko, B. Škugor, J. Deur, V. Ivanović, H. E. Tseng
SAE paper #2022-01-0814, SAE Int. J. Adv. & Curr. Prac. in Mobility, Vol. 4, No. 6, pp. 2469-2477
2022
The improvement of road transport safety requires the development of advanced vehicle safety systems, whose development could be facilitated by using complex interaction models of different road users. To this end, this paper deals with the modeling of multi-vehicle/multi-pedestrian interactions at unsignalized crosswalks. This multi-agent modeling approach extends on the existing basic model covering only single-vehicle/single-pedestrian interactions. The basic model structure and parameters have remained the same, as it was previously experimentally calibrated and thoroughly verified. The proposed modeling procedure employs the basic model within the multi-agent setting based on its application to relevant single-vehicle and single-pedestrian pairs. The resulting, so-called pre-decisions are then used for making final crossing decisions in a current time step for each agent. During the decision making process, each pedestrian takes into account approaching vehicles and their expected future behavior with respect to all pedestrians (i.e., himself/herself and other pedestrians), and vice versa for vehicles. This generalized multi-agent model is conceived to support simulation scenarios concerning multi-lane roads and pedestrians approaching from both sides of a road, as well. The model is verified by means of large-scale simulations and various scenarios.
simulation; modeling; calibration; game theory; roads and highways