High-precision map making method and system using millimeter wave radar

Abstract

The invention relates to a high-precision map making method and system using a millimeter wave radar, and belongs to the technical field of radar. The method comprises the following steps of acquiringroad information by using the millimeter wave radar in a process of enabling a vehicle provided with the millimeter wave radar to pass through a road section; identifying road characteristics; and generating a high-precision map according to the road information, the road characteristics and vehicle information. The method has low hardware cost, low false alarm rate, high data acquisition precision, many identifiable objects and low environmental requirements and can cope with the severe weather and scenes with the low visibility and the like; and furthermore, through a crowdsourcing way, thevehicles provided with the millimeter wave radars pass through the same road section or pass through the same road section for multiple times to acquire the road information for many time, so that amillimeter wave radar high-precision map layer is formed, the map is timely updated, and thus the generated high-precision map meets the requirement for automatic driving to be beneficial to large-scale commercial use.

Description

technical field [0001] The present invention relates to the technical field of radar, in particular to the technical field of millimeter-wave radar, and specifically refers to a high-precision map production method and system using millimeter-wave radar. Background technique [0002] High-precision maps are called the "eyes" of unmanned driving and are one of the core technologies of unmanned driving. Accurate high-precision maps can help cars perceive complex road surface information in advance, such as slope, curvature, heading, etc., combined with intelligent path planning, allowing cars to make correct decisions. The drawing of high-precision maps includes steps such as data collection. Data collection currently encounters many difficulties. The preferred solution in the prior art is the combination of laser radar, high-precision positioning and IMU (inertial navigation). The advantages of this solution are accurate data collection, detailed details, and better support ...

AI Technical Summary

Problems solved by technology

The advantages of this solution are accurate data collection, detailed details, and better support for autonomous driving. The disadvantages are that the cost of processing and collection is relatively high, the coverage is limited, the update is slow, and it is difficult to commercialize on a large scale.

Another emerging solution is the camera solution. The camera solution is more intuitive and convenient for large-scale commercial use, but it also has its limitations. bad

Images