Vehicle positioning method and device, vehicle and storage medium

Abstract

The embodiment of the invention relates to a vehicle positioning method and device, a vehicle and a storage medium. The vehicle positioning method comprises the following steps: identifying a site entrance; obtaining an indoor semantic map of the site according to the site entrance, wherein the indoor semantic map comprises semantic feature points of the site; correcting the positioning information of the vehicle in the indoor semantic map according to the semantic feature points obtained by the vehicle in motion; and acquiring positioning information of the vehicle according to the motion information of the vehicle relative to the previous semantic feature point. Because the selected features are semantic and easy-to-identify features of the road, the data volume of the points in each field is very limited, and the complexity of the processing algorithm is greatly simplified. The invention discloses a method for identifying points. The method is mainly used for identifying the physical quantities of the vehicle during running, the physical quantities are obtained by operation of other parts of the vehicle, and the identification process is correspondingly simplified greatly. For example, the slope-entering point can be identified based on posture and IMU, deceleration strips can be recognized by speed and IMU, and road joints can be identified by steering wheel and IMU.

Description

Technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a vehicle positioning method and device, a vehicle, and a storage medium. Background technique [0002] The existing positioning technology in automatic driving mainly uses satellite positioning signals for positioning, such as GPS (Global Positioning System, Global Positioning System) signals or Beidou satellite signals for positioning, but when there is no satellite signal, other methods are needed for positioning. Since there is no satellite signal mainly indoors, such as an underground parking lot, etc., positioning without satellite signals can also be called indoor positioning. [0003] The existing mainstream indoor positioning technology for autonomous driving uses visual acquisition mapping or lidar mapping, and positioning is performed based on the map. The advantages and disadvantages of visual positioning or lidar indoor positioning technology are very obv...

AI Technical Summary

Problems solved by technology

The advantages and disadvantages of visual positioning or lidar indoor positioning technology are very obvious. First, the processor needs to have very powerful computing power, so that it can process huge video data; Difficult, the continuous accumulation of feature points will lead to the accumulation of a huge amount of data in a small map; thirdly, the entire set of hardware equipment for processing visual algorithms is complex and expensive

Images