Automatic driving vehicle positioning method, device and electronic device based on vehicle-road coordination

Abstract

The present application discloses a method, device and electronic device for positioning an autonomous driving vehicle based on vehicle-road coordination. The method includes: acquiring a reference position information set of a vehicle sent by a roadside device, where the reference position information set is based on the roadside The grid map established by the device within its visible range is obtained; the reference position information of the own vehicle is determined according to the reference position information set of the vehicle; according to the reference position information of the own vehicle, as well as the size information of the own vehicle and the own vehicle Determine the absolute position information of the own vehicle; perform fusion positioning according to the absolute position information of the own vehicle, and obtain the fusion positioning result of the own vehicle. The automatic driving vehicle positioning method based on the vehicle-road coordination of the embodiment of the present application determines the position of the self-vehicle by using the position information of all vehicles within the visible range provided by the roadside device, and then obtains the final fusion positioning result of the self-vehicle through the fusion positioning process. It ensures the positioning accuracy and stability in extreme environments or extreme weather.

Description

technical field [0001] The present application relates to the technical field of autonomous driving, and in particular, to a method, device and electronic device for positioning an autonomous driving vehicle based on vehicle-road collaboration. Background technique [0002] High-precision positioning is very important for autonomous vehicles. The higher and more stable the positioning accuracy, the safer the autonomous vehicle will be. At present, the mainstream positioning scheme is mainly based on integrated navigation. For example, the Kalman filter is used to fuse the high-frequency IMU (Inertial Measurement Unit, inertial measurement unit) positioning signal and the low-frequency GNSS (Global Navigation Satellite System, Global Navigation Satellite System) positioning. signal, output the positioning result with high frequency and no accumulated error. [0003] With the development of hardware and multi-sensor fusion positioning technology, the SLAM (Simultaneous Locali...

AI Technical Summary

Problems solved by technology

[0004] However, due to the multipath effect caused by high-rise buildings and viaducts in the city, the accuracy of GNSS positioning signals will be greatly reduced. The premise of using laser SLAM or visual SLAM methods is to have map data, such as maps created by lasers, high-precision Maps or semantic maps, etc., and in many scenarios, this method cannot obtain reliable results, such as scenarios where there is snow and water on the road, or there are many dynamic objects around the car.

Images