کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون

صفحه اصلی / هشتمین کنفرانس بین المللی کنترل ، ابزار دقیق و اتوماسیون

Decision Making for Autonomous Vehicles' Strategy in Triple-Lane Roundabout Intersections

نویسندگان :

Shadi Samizadeh¹ Amirhossein Nikoofard² Hossein Yektamoghadam³

1- دانشگاه صنعتی خواجه نصیرالدین طوسی 2- دانشگاه صنعتی خواجه نصیرالدین طوسی 3- دانشگاه صنعتی خواجه نصیرالدین طوسی

کلمات کلیدی :

roundabout intersection،autonomous vehicles،decision Making،genetic algorithm،traffic optimization

چکیده :

The efficiency of roundabout intersections plays a vital role in traffic flow. With the increase of autonomous vehicles on roads in the future, vehicle-to-infrastructure (V2I) communications would improve traffic efficiency in roundabout intersections. In this paper, we investigate the throughput of a triple-lane roundabout intersection that has no traffic light to see which lane has the minimum waiting time. To do this, we utilize a decision-making algorithm that first determines which lane is the best (has the least waiting time) in each iteration. Then, the algorithm investigates the convergence of the best lane. Finally, the scenarios of a working day and a holiday that have different traffic flows are compared. The results show that there is no preference among lanes in the holiday as we expected. But in the working day, the algorithm converges to one of the lanes.