Driving decision-making analysis of lane-changing for autonomous vehicle under complex urban environment

Lane-changing decision-making is critical to complete driving mission for autonomous vehicles under complex urban environment. The complex information (such as the running conditions of interfering vehicles, signal lamp, and road facilities) have a great influence on autonomous vehicle's lane-changing decision. This paper proposes to use the Rough Set theory to abstract the lane-changing rules to support the decision-making of autonomous vehicles under the complex urban environment. Firstly, a virtual urban traffic environment is built by Prescan (a simulation environment for developing advanced driver assistant system). Secondly, the Rough Set theory is proposed to reduce the influence of weak interdependency data, and extract the driver's decision rules. Finally, the result is that: 1) During the intention generation process of lane-changing, the decision-making a is associated only with the relative distance between the subject Car and the interfering Car2 (D₂) and the relative velocity between the subject Car and the leading Car1 (V₁). 2) Both of the decision-making rules during intention generation and implementation phase process are extracted based on Rough Set method, which provide a theoretical basis for the lane-changing decision-making under complex urban environment.