A conflict–congestion model for pedestrian–vehicle mixed evacuation based on discrete particle swarm optimization algorithm

A simulation model based on temporal–spatial conflict and congestion for pedestrian–vehicle mixed evacuation has been investigated. Assuming certain spatial behaviors of individuals during emergency evacuation, a discrete particle swarm optimization with neighborhood learning factor algorithm has been proposed to solve this problem. The proposed algorithm introduces a neighborhood learning factor to simulate the sub-group phenomenon among evacuees and to accelerate the evacuation process. The approach proposed here is compared with methods from the literatures, and simulation results indicate that the proposed algorithm achieves better evacuation efficiency while maintaining lower pedestrian–vehicle conflict levels.