High-precision point cloud map construction method

Abstract

The embodiment of the invention relates to a high-precision point cloud map construction method. The method comprises the following steps of: receiving first sensor data sent by a terminal; judging whether the first sensor data meets a data qualification judgment rule or not; when the first sensor data meets the data qualification judgment rule, obtaining second sensor data according to the sensordata; constructing a point cloud map according to the second sensor data, the point cloud map comprising first positioning data; and when the point cloud map meets a precision condition, a distortioncondition, a smoothness condition, a continuity condition and an integrity condition, determining that the point cloud map passes verification. According to the high-precision point cloud map construction method provided by the embodiment of the invention, the quality of the point cloud map is improved, and a plurality of point cloud map tasks can be executed at the same time.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to a method for constructing a high-precision point cloud map. Background technique [0002] At present, the point cloud map construction methods that are widely used in the autonomous driving industry can be roughly divided into two types: point cloud map construction methods based on offline data and point cloud map construction methods based on online data. [0003] The point cloud map construction method based on offline data, if the point cloud map construction is completed offline based on the vehicle end, it not only requires high performance of the vehicle processor, it is difficult to handle large maps, the quality and error of the map cannot be guaranteed, and it is impossible to complete multiple maps at the same time. Point cloud map construction; if the point cloud map construction is completed offline based on a local desktop, it involves cumbersome processes...

AI Technical Summary

Problems solved by technology

[0003] The point cloud map construction method based on offline data, if the point cloud map construction is completed offline based on the vehicle end, it not only requires high performance of the vehicle processor, it is difficult to handle large maps, the quality and error of the map cannot be guaranteed, and it is impossible to complete multiple maps at the same time. Point cloud map construction; if the point cloud map construction is completed offline based on a local desktop, it involves cumbersome processes such as data download, software start-up, and result data upload. The scene point cloud map is constructed at the same time, which seriously wastes human resources and local computing resources

[0004] The point cloud map construction method based on online data, because the point cloud map construction tasks are completed in the vehicle processor, the performance requirements of the vehicle processor are very high, the large map is difficult to handle, the map quality cannot be guaranteed, and the point cloud map verification is missing. Late data accumulation is not friendly, and multiple point cloud map construction tasks cannot be realized at the same time due to vehicle and scene limitations

Images