For non-scanning laser radar, Flash LiDAR is a scanning laser pointer radar, which emits an area of light. For example, Ledder Tech in Switzerland developed products such as Flash liDAR. At present, in fact, the industry’s current driving force is quite large, including ourselves, and the main research and development efforts are also focused on solid-state lidar. I believe that everyone will soon see that this low-cost lidar, from R & D, samples to commercial use, may have a faster cycle than originally expected. Because not a lidar company is working hard, but the entire industry chain is working hard.
Massive point cloud data expressing the spatial distribution of the target and the surface characteristics of the target in the same space advocacy department. The generating device can be produced by a lidar or a depth camera. According to the point cloud obtained by lidar, it includes three-dimensional coordinates (XYZ) and laser reflection intensity (Intensity). The most important part of the application of lidar in automatic driving is positioning: the position is determined, and the unmanned vehicle only knows where and how to go. Therefore, determining “Where am I” is the first step and a very critical step.
At present, RTK and differential GPS are used for positioning. Lidar or vision are also used. But RTK will still be disturbed by the signal. Especially in some cities, buildings and trees, as well as in and out of the tunnel, its signal is easily interrupted. Another is based on visual positioning. In fact, it is related to the characteristics of his vision itself and has a strong dependence on the environment. For example, under backlighting or rain and snow, this positioning is easy to fail.
For the positioning of lidar, we get a predicted global position through IMU, inertial navigation system, encoder and GPS. When the red laser pointer radar scans a single point cloud data in real time, we will combine the single point cloud data to match and perform feature extraction.
These features include features such as roadsides, lane lines, and other surrounding points, lines, and surfaces. For high-precision maps, the extracted features are matched with the features extracted in real time to finally obtain accurate vehicle body speed. This is the positioning process of lidar.