Multi-laser radar fusion method based on vehicle-road cooperation

Abstract

The invention provides a multi-laser radar fusion method based on vehicle-road cooperation, belonging to the technical field of automobiles. The invention aims to solve the problem that accurate and complete target data cannot be provided for people in the prior art. The multi-laser radar fusion method based on vehicle-road cooperation comprises the following steps: performing point cloud processing on target information detected by laser radars installed at a road end and a vehicle end to obtain point cloud data corresponding to the laser radars; conducting clustering, tracking and space synchronization processing on the point cloud data in sequence to form target lists corresponding to the laser radars; performing time synchronization processing on each target list to obtain each targetlist at the same moment; extracting all the point cloud data corresponding to the same target in each target list at the same moment; and performing clustering and tracking processing on all the extracted point cloud data in sequence, and then performing fusion to form a final target list. According to the invention, sensing information with higher precision and better stability can be obtained.

Description

technical field [0001] The invention belongs to the technical field of automobiles, and relates to a multi-laser radar fusion method based on vehicle-road coordination. Background technique [0002] In recent years, smart cars (or unmanned cars, self-driving cars) have become a research hotspot in the field of automotive engineering in the world and a new driving force for the growth of the automotive industry. [0003] Perception fusion is a research hotspot in the field of intelligent driving, and a large number of new fusion technologies have been proposed. For example, in functions such as automatic parking assistance system and automatic valet parking, the fusion of surround view camera, ultrasonic radar, millimeter wave radar and other information can help the car complete obstacle avoidance, find parking spaces and other actions. In the side functions such as blind spot detection, door opening warning, and change to warning, through the fusion of various sensors such...

AI Technical Summary

Problems solved by technology

[0004] However, the existing single-vehicle-based multi-lidar fusion schemes, such as lidars installed on the roof and front and rear of the vehicle, cannot detect distant or occluded targets, nor can they deal with sudden appearance of targets. emergency scenarios; in addition, although there are solutions for roadside installation of lidar in the existing technology, and with the maturity of 5G technology and road infrastructure, the development of technologies such as vehicle networking V2X and vehicle-road coordination has been accelerated.

The communication and interaction between vehicles and between vehicles and roads can be realized through cellular network or WIFI technology. However, in the existing technology, the target data detected by the road-end lidar and the vehicle-end lidar exist independently, which cannot be given People provide an accurate and complete target data, but there is a problem of low accuracy and effectiveness of the perception of targets and obstacles

Images