A Preliminary Evaluation of Activity Scheduling Optimization Using Real Data from a Household Travel Survey

Intelligent transportation systems enable major innovations in road traffic, public transportation services, and personalized route planning. However, the application of intelligent planning solutions and the enhanced integration of mobility services are not entirely unfolded. A novel approach known as Activity Chain Optimization (ACO) allows travelers to optimize their travel time during their daily activity schedules. The purpose of this study is to adapt the ACO approach to evaluate its performance using household survey data. The optimization process is constructed using genetic algorithms with tuned parameters. The results show that the ACO approach performs better in the case of larger activity chains. Furthermore, the travel time in the optimized scenarios is shorter than in the non-optimized base scenarios. Therefore, travelers can save time and reduce emissions by using the ACO approach when carrying out daily activities.