|
Category | Variable | Description | Reason for clustering |
|
Road | Dry/wet | Wet and dry conditions of the road surface, including dry and wet | Different road types have an impact on the implementation of different collision avoidance strategies, while the dry and wet conditions of the road surface have an impact on the ground adhesion coefficient |
TYPE_R | Types of road, including crossroads, T-intersection, and ordinary roads |
|
Environment | Obstruct | Whether the TW has a blind spot to car | Environmental factors can have an impact on the radar and cameras of autonomous vehicles |
Weather | Weather conditions, including sunny, cloudy, and severe weather |
Time | The time of the accident, including daytime, nighttime, and morning-evening |
|
Car | TYPE_Car | Types of cars, including sedan and nonsedan (SUV, MPV) | Different types of cars affect where sensors are installed, and the car’s precrash driving behavior affects the active safety system’s decision-making |
BEHAVIOR_Car | The driving behavior of car, including straight, left, and right |
|
TW | TYPE_TW | Types of TW, including traditional bicycles, electric TWs, and motorcycles | As an identification target, the type and physical appearance of the TW have an impact on the identification and tracking of the active safety system |
BEHAVIOR_TW | The driving behavior of TW, including straight, left, and right |
Relative | The direction of motion of TWs relative to cars, including incoming traffic from the left (Left), incoming traffic from the right (Right), traveling in the same direction (Same), and traveling in opposite directions (Opposite) |
Helmet | Whether the driver of a TW wears a helmet |
|