Road information fusion system and method for autonomous driving vehicles

Abstract

The invention relates to the field of intelligent transportation, and provides a road information fusion system and method for automatic driving vehicles. Wherein, the road information fusion system includes: an information acquisition unit, used to acquire various types of road information collected by various types of road perception sensors of the vehicle; an information initial fusion unit, used to process the various road information Initial fusion, wherein the initial fusion includes information preprocessing and information validity verification; and an information depth fusion unit, which is used to deeply fuse the various road information after the initial fusion to output the road model of the vehicle, wherein The deep fusion includes information coordinate transformation, road feature point extraction, lane line fitting, lane line calculation and information comprehensive management. The present invention performs initial fusion and secondary fusion on similar road information, reduces repeated data processing processes, and improves the accuracy of an output road model.

Description

technical field [0001] The invention relates to the field of intelligent transportation, in particular to a road information fusion system and method of an automatic driving vehicle. Background technique [0002] At present, vehicles with Autonomous Driving System (ADS) have been gradually introduced to the market, which has greatly promoted the development of intelligent transportation. ADS uses the environment perception system installed on the vehicle to perceive the surrounding environment in real time, and determines the drivable area of ​​the vehicle through the data returned by the sensor. Among them, the content of environmental perception can be divided into two parts, namely road information and target information, in which the target information can provide the ADS decision-making system with the targets of various areas around the vehicle, so that the decision-making system can make correct responses (overtaking, Behaviors such as deceleration and following) to ...

AI Technical Summary

Problems solved by technology

[0003] However, in the prior art, road information is mainly detected by a single road perception sensor (such as a vehicle camera), and the detection method is relatively single, and there are problems of false detection and missed detection, and the attributes of the road information output by a single road perception sensor are different. comprehensive, unbalanced

In addition, in some schemes that use different road perception sensors to detect road information, there is also a lack of data processing and data fusion mechanisms for road information obtained by different sensors, which is not conducive to ensuring the accuracy of the obtained output road model

Images