Vehicle lane changing prediction method and device, equipment and vehicle

Abstract

The embodiment of the invention discloses a vehicle lane changing prediction method. The method comprises the following steps: determining whether a target vehicle has a lane changing intention or notaccording to motion state information of the target vehicle; if the lane changing intention exists, determining a real lane changing category according to the motion state information of the target vehicle at the current moment and the previous moment; if the real lane changing category is a preset category, determining the motion trails of the target vehicle and the surrounding vehicles; and determining a lane changing result of the target vehicle according to the motion trail. According to the vehicle lane changing prediction method provided by the embodiment of the invention, the lane changing intention of the target vehicle is predicted by utilizing the motion state information of the target vehicle at the current moment and the previous moment, and whether lane changing can be successful or not is predicted by utilizing the motion state information of the target vehicle and the surrounding vehicles, so that more accurate and reliable lane changing prediction of the target vehiclecan be realized, and the safety of automated driving is enhanced.

Description

technical field [0001] Embodiments of the present invention relate to the technical field of vehicle automatic driving, and in particular to a prediction method, device, equipment and vehicle for vehicle lane change. Background technique [0002] At present, autonomous driving technology is developing rapidly, and mid-to-high-end models at home and abroad are all equipped with automatic driving functions. In mass-produced vehicles equipped with ADAS functions, in addition to the perception and judgment of target signals such as surrounding obstacles, it is also necessary to have the ability to predict the movement trend of surrounding vehicles. [0003] At present, most of the methods are traditional machine learning methods, which take the given real-time state information of the vehicle as input and the vehicle's lane change intention as output. These methods obtain the best prediction results by inferring the mapping function. This type of method only uses information at...

AI Technical Summary

Problems solved by technology

This type of method only uses the information at a certain moment, and cannot deal with the complex interaction information between time series information and vehicles.

Images