Autonomous vehicle driving environment cognitive target selection method and device and storage medium

Abstract

The invention discloses an autonomous vehicle driving environment cognitive target selection method and device and a machine readable storage medium. The method comprises the steps: 1, acquiring perception information and vehicle information from a vehicle perception interface; 2, establishing a boundary line model for the driving environment according to the perception information and the vehicle information; 3, establishing a boundary line arbitration module, and selecting an optimal boundary line model of the current scene; and 4, according to the optimal boundary line model, putting the targets into the corresponding lanes in sequence, and filtering the targets exceeding the boundary line. According to the method, a plurality of models are established for the driving environment of the automatic driving vehicle by collecting the information data of the sensor and the vehicle, the target in the driving road is selected, accurate and effective information is provided for automatic driving vehicle trajectory planning, and the problems of target selection robustness, adaptability and the like in the prior art are partially solved.

Description

technical field [0001] The invention belongs to the field of automobile intelligent driving, and in particular relates to a method for selecting an environment cognition target. Background technique [0002] In the vehicle automatic driving system, it mainly includes environmental perception fusion, environmental cognition, and planning control modules. Among them, environmental cognition plays a link between the preceding and the following. The vehicle automatic driving system first needs to receive information from the fusion of environmental perception, such as target information, lane line information, traffic sign information, etc.; then, it needs to perform a series of processing on the environmental perception information , to obtain accurate information required by the planning control module, so as to ensure the safe and effective motion control of the vehicle by the planning control module. [0003] In the environmental cognition module, target selection is crucia...

AI Technical Summary

Problems solved by technology

[0004] Aiming at the deficiencies in the prior art, the present invention proposes a method, device, and machine-readable storage medium for selecting an environment cognition target for an autonomous vehicle, for at least part of the To solve the problems of target selection robustness and adaptability in the environmental cognition module of autonomous driving vehicles existing in the background technology, it establishes multiple models for the driving environment of autonomous driving vehicles by collecting sensor and vehicle information data, and selects the driving road To provide accurate and effective information for trajectory planning of autonomous vehicles

Images