Data fusion method and device for intelligent vehicle

Abstract

The invention discloses a data fusion method and device for an intelligent vehicle. The method comprises the following steps: acquiring initial data at an Mth moment based on a plurality of sensing devices of the intelligent vehicle; wherein M is an integer greater than 1; fusing the initial data at the Mth moment to obtain fused data at the Mth moment; processing the fused data based on a Kalman filtering model to obtain an estimated value xM of the motion state at the Mth moment; and processing the estimated value xM based on an XGBoost model to obtain a solution of a target motion state. According to the technical scheme of the invention, data fusion is carried out on the data acquired by the vehicle-mounted environment sensing sensor and the V2X equipment, and data estimation is optimized based on the Kalman filtering model and the XGBoost model, so that data full fusion is finally realized, the precision of data fusion is improved, and the data fusion efficiency is improved. The problems of low estimation data fusion precision and insufficient data fusion in the prior art are solved.

Description

technical field [0001] The invention belongs to the technical field of automatic driving, and in particular relates to a data fusion method and device for intelligent vehicles. Background technique [0002] Due to the diversity and complexity of the road environment and weather environment, as well as the motion characteristics of the intelligent driving vehicle itself, there is no perfect sensing device, and it is normal for the device to be unsatisfactory, and there is no perfect data fusion algorithm; however, for different driving tasks In other words, different types and types of sensing devices are required, and it is not necessary to configure the most complete, most, and expensive sensing devices to complete the driving task; since autonomous autonomous driving is equipped with a variety of on-board sensing devices, a single on-board Sensing equipment has a small range of perception of the environment, and its ability to perceive the environment is relatively limited...

AI Technical Summary

Problems solved by technology

[0003] However, the sensors in the prior art autonomous driving work alone. When the vehicle is used under different environmental conditions, different sensor data are perceived separately, so the output perception results in different environments are not stable and reliable, and the environmental perception is poorly adaptive. The problem of poor robustness of the system, and the existing multi-source sensor data fusion scheme is based on the data fusion realized by the Kalman filter algorithm, there will be a time delay when multiple sensors acquire video information, and the existing Kalman filter algorithm has no effect on the filtering process. The noise interference processing is not sufficient, the above problems lead to the adequacy and accuracy of data fusion are affected

Images