Automobile driving obstacle detection method and system based on multiple laser radars

Abstract

The invention discloses an automobile driving obstacle detection method and system based on multiple laser radars, and belongs to the field of sensor data perception in the field of automatic driving.The core of an automatic driving function comprises sensing, fusion, decision making, planning and control, and the sensing of the sensor data is the first step of realizing the automatic driving function. According to the invention, obstacle detection is carried out by using the multiple laser radars, and the velodyne-16 line laser radars are installed at the left side, the right side and the roof of an automobile respectively and are used for sensing the surrounding environment of the automobile, obstacles are obtained, and data support is provided for path planning of a decision-making module. A high-precision map and the laser radars are combined, a bit depth image of the laser point cloud is used for obstacle detection, the detection efficiency is greatly improved, the 16-line laserradars are used for obstacle detection, and the use cost is greatly reduced.

Description

technical field [0001] The invention relates to the field of vehicle driving obstacle detection, and more specifically, relates to a multi-laser vehicle driving obstacle detection method and system. Background technique [0002] The core of the autonomous driving function includes sensor data perception, fusion, decision-making, planning, control and other parts. Among them, the perception of sensor data is the first step in the realization of automatic driving functions. At present, the main automatic driving perception at home and abroad is used. LiDAR is used for obstacle detection, and many use 32-line or 64-line LiDAR for obstacle detection, but this kind of LiDAR is expensive and not suitable for mass use. [0003] There are many ways for lidar to detect obstacles. 1) Perform 2D projection transformation on lidar to the image coordinate system and use connected domains to detect obstacles. 2) Use K-D tree and Euclidean clustering to detect obstacles. 3) Convert the...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a multi-lidar vehicle for the technical defect that the method for detecting obstacles by laser radar in the prior art takes a relatively long time and cannot provide support for scenes with strict real-time requirements. Driving obstacle detection method and system

Images