Details

Autor(en) / Beteiligte

• Xue-mei, Chen
• Zi-jia, Wang
• Meng-xi, Li
• Yang-jia-xin, Ou

Titel

A Multiple-Vehicle Decision-Making Model for Left-Turn Behavior of AVs at Urban Intersections based on conflict resolution

Ist Teil von

• 2020 7th International Conference on Information Science and Control Engineering (ICISCE), 2020, p.1565-1571

Ort / Verlag

IEEE

Erscheinungsjahr

2020

Quelle

IEEE/IET Electronic Library (IEL)

Beschreibungen/Notizen

• In the complex and dynamic urban road environment, conflicts in time and space between different traffic participants are inevitable. In this paper, a model to predict the trajectories of oncoming straight vehicles is proposed based on the Gaussian Process Regression (GPR) model with the consideration of analysis of left-turn potential conflict behaviors. Then, a conflict resolution method for left-turn behavior of autonomous vehicles at urban intersections and a driving action selection method considering multiple factors, such as safety, efficiency, comfort and altruism, are proposed. Experiments show that the model can guide the unmanned vehicles to complete the task with a success rate of more than 90%. The research results can provide decision-making support for autonomous vehicles passing through urban intersections safely.