A Feasibility Study on a Traffic Management System for Autonomous Driving Services based on Dynamic Map

An autonomous driving service in urban areas is still a challenging problem. It is necessary to simultaneously solve tactical planning problems and operation planning problems, such as a scenario for passing through an intersection with oncoming vehicles. To realize the service by using a centralized management system, it is necessary to guide thousands of vehicles in real-time. Therefore, efficiency and robustness are required for the management system. In this study, we propose a centralized path planning system to make tactical level decisions to manage the path plans of multiple vehicles based on Dynamic Map. The proposed system selects an operational-level planner to generate a detailed motion plan for each vehicle based on a decision-making algorithm. Then, the conflicts of motion plans between vehicles are detected and resolved by using a spatio-temporal reservation map on Dynamic Map. We report the results of simulation tests of10,000 hours to evaluate the efficiency and robustness of the proposed system using the map data of an existing city.