Host: The Japanese Society for Artificial Intelligence
Name : The 38th Annual Conference of the Japanese Society for Artificial Intelligence
Number : 38
Location : [in Japanese]
Date : May 28, 2024 - May 31, 2024
Cities are complexes of diverse social systems, where many people interact and complex social phenomena constantly occur. In order to analyze, optimize and efficiently control activities in such complex urban environments, multi-agent social simulation (MASS) is effective. However, manipulating MASS and understanding the effects of measures is not easy for non-specialists in information technology. The authors are working on the development of a MASS-based stakeholder participatory policy planning support tool. Focusing on the transport sector, this paper reports on a prototype system consisting of a multi-agent traffic simulation, a visualization environment for simulation data and a web application for simulation operations. A social experiment is conducted in which the system is used by the general public and, based on the feedback, the development issues to be addressed in order to develop the system into a practical system are discussed.