A data fusion method and device

Abstract

This application discloses a data fusion method and device, by correcting the driving data of the obstacles around the target vehicle detected by the millimeter-wave radar and the driving data of the obstacles around the target vehicle detected by the laser radar, and then performing the correction result Fusion processing, so that more accurate obstacle detection results can be matched. The method includes: firstly, correcting the driving data of the obstacles around the target vehicle detected by the millimeter-wave radar to obtain the corrected first target data, and performing a correction on the driving data of the obstacles around the target vehicle detected by the laser radar. Instantaneous displacement filling to obtain the filled second target data, and then facilitate EKF to perform fusion processing on the obtained corrected first target data and filled second target data, so as to determine the surrounding area of ​​the target vehicle according to the fusion result Obstacle detection results.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a data fusion method and device. Background technique [0002] In the field of autonomous driving, especially unmanned driving, it is necessary to clarify the relative displacement of other vehicles and the own vehicle. At present, the self-vehicle generally detects the relative positions of other surrounding vehicles and the self-vehicle through millimeter-wave radar and lidar. [0003] However, the inventor found through research that, no matter whether the millimeter-wave radar or the laser radar is used to detect the relative positions of other surrounding vehicles and the self-vehicle, the detection is inaccurate. Specifically, since the millimeter-wave radar uses the reflection of the target object on the electromagnetic wave to find and measure the position of the surrounding objects, while the vehicle is driving, the external environment full of clutter...

AI Technical Summary

Problems solved by technology

[0003] However, the inventor found through research that, no matter whether the millimeter-wave radar or the laser radar is used to detect the relative position of other vehicles around and the own vehicle, the detection is inaccurate.

Specifically, since the millimeter-wave radar uses the reflection of the target object on the electromagnetic wave to find and measure the position of the surrounding objects, while the vehicle is driving, the external environment full of clutter will have a negative impact on the detection of the millimeter-wave radar, reducing the detection of objects. Detection accuracy

At the same time, it takes a certain amount of computing time to obtain data through point cloud recognition through lidar, and during the calculation process of the point cloud recognition algorithm, the own vehicle and other surrounding vehicles still continue to move, so the other vehicles obtained by the point cloud recognition algorithm and There is a certain delay difference between the relative displacement of the self-vehicle and the actual relative displacement, that is, the relative displacement of other vehicles and the self-vehicle obtained by the point cloud recognition algorithm has a lag and inaccurate problem, which will also lead to inaccurate detection results

Images