An Accurate Autonomous Vehicles Positioning Method Based on GPS/Lidar/Camera in V2V Communication Environment

In the field of autonomous vehicles, accurate positioning is vital to perception and motion planning and control. To solve the problem that the global positioning system (GPS) cannot function properly due to signal loss or block in certain GPS-denied environments, we propose an accurate positioning method that fuses multiple data sets. First, we utilize 3D Lidar data to generate object-region proposals and map these candidates into the image space. Then, we acquire the GPS information of the neighboring vehicles through the V2V communication. After obtaining the relative position and global position of the adjacent vehicle, we can use an inverse UTM projection to determine the global position coordinate of the ego-vehicle. Experiments show that our method can obtain the accurate global positioning result in the tunnel or urban canyon where the GPS signal is obstructed.