ABSTRACT This paper introduces MOMSATC, an innovative multi‐objective, multi‐step adaptive traffic signal control framework grounded in the principles of model predictive control. MOMSATC is specifically designed to address complex, high‐dimensional optimisation challenges, including the mitigation of pedestrian and vehicle safety risks alongside delay management. The framework first establishes a hybrid safety evaluation model to comprehensively assess conflicts involving vulnerable road users, providing input to a multi‐task learning model that predicts safety and delay outcomes. Safety risks are translated into a quantifiable monetary cost equivalent using a willingness‐to‐pay approach that considers long‐term health and socio‐economic impacts. The overarching aim of MOMSATC is to support an interpretable decision process that can represent objective priorities in a transparent manner. By integrating predictive modelling with a structured optimisation procedure, the framework allows pedestrian safety to be prioritised while maintaining a balance between vehicle safety and overall operational efficiency. A case study demonstrates the efficacy of MOMSATC, achieving significant reductions in safety risks for both pedestrians and vehicles, with moderate trade‐offs in delay, underscoring its potential to achieve a safety‐orientated urban transport system.
Chan et al. (Thu,) studied this question.