Obstacle recognition method, device, electronic device and storage medium

Abstract

The present application discloses an obstacle identification method, device, electronic equipment, and storage medium, and relates to the field of automatic driving, wherein the method may include: acquiring roadside perception information during the driving process of the main vehicle, the main vehicle being the vehicle to be identified; For any acquired frame of roadside perception information, perform the following processing: if the current frame is not in the defined abnormal state, identify the main vehicle obstacle in the roadside perception information according to the main vehicle information corresponding to the current frame, and cache The main vehicle information corresponding to the current frame; if it is currently in an abnormal state, estimate the main vehicle information corresponding to the current frame based on the latest cached main vehicle information, and identify the main vehicle obstacle in the roadside perception information based on the main vehicle information corresponding to the current frame object, and cache the main vehicle information corresponding to the current frame. Applying the scheme described in this application can improve the robustness and fault tolerance of the main vehicle obstacle recognition.

Description

technical field [0001] The present application relates to the field of computer applications, in particular to an obstacle recognition method, device, electronic equipment and storage medium in the field of automatic driving. Background technique [0002] During the driving process of unmanned vehicles, the information of obstacles can be obtained by means of roadside perception information, so as to effectively avoid obstacles and so on. [0003] From the perspective of roadside perception, unmanned vehicles themselves will appear in the perception results like other vehicles and pedestrians, that is, they will be regarded as obstacles. Therefore, in order to ensure the normal driving of unmanned vehicles, it is necessary to The human-driven vehicle is removed from the obstacles in the roadside perception information. [0004] For example, the vehicle's positioning information can be used to identify obstacles that are unmanned vehicles from the obstacles in the roadside p...

AI Technical Summary

Problems solved by technology

However, the robustness and fault tolerance of the existing identification methods are poor. Once an abnormality occurs, such as an abnormal positioning, it cannot be accurately identified.

Images