Ramp intersection recognition method and vehicle for automatic driving

Abstract

The invention belongs to the technical field of automatic driving, and discloses an automatic driving ramp entrance identification method and a vehicle. The automatic driving ramp entrance identification method includes the following steps: obtaining the position information of the vehicle on the expressway; When the distance from the ramp is the discriminant distance, start to identify the exit signs on the right side of the expressway; before the last exit sign, each time an exit sign is recognized, the number of the identified exit and the number of the exit to be driven are compared. Carry out comparison and confirmation; when the last exit sign is recognized, the final comparison and confirmation will be carried out between the identified exit number and the exit number to be driven out, and the ramp exit guide line will be identified; the ramp exit guide line will be controlled The vehicle drives out from the expressway, and the vehicle can execute the above-mentioned ramp identification method for automatic driving. The invention can realize the identification of the ramp entrance at a lower cost, so as to control the vehicle to drive out of the expressway through the ramp.

Description

technical field [0001] The invention relates to the technical field of automatic driving, in particular to an automatic driving ramp identification method and a vehicle. Background technique [0002] At this stage, the more practical application scenarios of autonomous driving technology are structured roads - expressways. Exiting the highway through the ramp is a technical point for self-driving vehicles. The difficulty lies in how to use a variety of sensor fusion technologies to know and judge the location of the highway ramp in advance, and to change lanes in advance to exit the highway. [0003] For this technical point, the existing automatic driving control methods mainly fall into two categories: [0004] 1. Rely on high-precision maps collected by lidar for high-precision positioning, and obtain prior geographical elements and precise location information from the map. However, due to the high cost of high-precision map production and the need to occupy a large am...

AI Technical Summary

Problems solved by technology

However, due to the high cost of high-precision map production and the need to occupy a large amount of local storage space, it is not conducive to the promotion and use of mass-produced models.

[0005] 2. Based on the method of lane line recognition and navigation map, this type of method is low in cost and easy to promote, but the stability and recognition rate of the system are low

Images