An Autonomous Overtaking Maneuver Based on Relative Position Information
Meihong Zhang, Tingting Zhang, Qinyu Zhang · 2018
Reliable and efficient overtaking maneuvers are important and challenging for autonomous vehicles. Position information of both involved vehicles during overtaking is important, to avoid collisions. In this paper, we try to perform overtaking based on relative position information, such as the distance, angle and velocity between vehicles, in a non-collaborative scenario. To reduce the complexity of maneuvers, a fuzzy inference system (FIS) is applied to analyze the driving behavior of the preceding vehicle based on the relative position information. An output of “safe” or “dangerous” will be sent to the decision part based on reinforcement learning frameworks. Various overtaking maneuvers including “conservative” and “aggressive” can be obtained accordingly. Numeric results validate our analysis, and show that our proposed strategies can be easily extended to the multiple-vehicle-scenario.