What are the specific applications of lidar in driverless driving?

1. Positioning
Positioning in unmanned driving for ten minutes is important. Only with real-time location information can the system make the next interpretation, decide where to go, and how to get there. There are many ways to position it now. Such as carrier phase difference technology (RTK), but RTK is still subject to signal interference. Especially in some cities, buildings and trees, as well as tunnels and tunnels, its signal is easily interrupted. At the same time, sensors such as cameras are also used to sense the external environment, construct an environmental model, and use the model to determine the location of the vehicle, but its dependence on the environment is relatively strong, such as backlighting or rain and snow, such positioning is prone to failure. LiDAR relies on comparing the initial position of the vehicle with the high-precision map information to obtain a precise position. First, sensors such as GPS, IMU, and wheel speed give an initial (probably) position. Secondly, the local point cloud information of the lidar is extracted, and the vector features in the global coordinate system are obtained by combining the initial positions. Finally, the vector features of the previous step are matched with the feature information of the high-precision map to obtain accurate global positioning. Therefore, in terms of positioning, the use of laser radar has an unparalleled advantage in terms of accuracy and stability.
2. Detection and classification of obstacles
Lidar does not rely on illumination, its viewing angle is 360 degrees, the calculation is relatively small, and it can be scanned in real time. It is generally used within 100 milliseconds. In the process of scanning, the laser radar first identifies obstacles, knows the position of the obstacle in space, and then classifies according to the existing obstacles. For example, cars and people, we divide these obstacles into independent individuals, and then separate and separate the individual to match, so as to classify the obstacles and track the objects. The process of tracking, first of all, is to divide the point cloud, and to make the associated target through the point cloud. We know whether the last one and the next one belong to the same object, then perform target tracking and output target tracking information.

Nowadays, the common detection principle of lidar is the time-of-flight method, which is to continuously transmit light pulses to the target, then receive the light returned from the object by the sensor, and obtain the target distance by detecting the flight round-trip time of the light pulse.