Method and device for predicting movement trajectory of obstacles at intersection

Abstract

The embodiment of the present invention proposes a method and device for predicting the trajectory of an obstacle at an intersection. The method includes: acquiring the environmental information at the intersection of the road that the vehicle will pass through and the information of visible obstacles within the vehicle's perception range; Fusion with the visual obstacle information to screen out the obstacle information in the blind area of ​​the vehicle at the intersection of the road; predict the trajectory of the obstacle corresponding to the obstacle information in the blind area according to the road information. The device includes: an acquisition module, which is used to obtain the environmental information of the road intersection that the vehicle will pass through and the visual obstacle information of the vehicle; the fusion module, which is used to filter out the blind spot obstacle information of the vehicle at the road intersection; the trajectory prediction module, It is used to predict the trajectory of the obstacle corresponding to the obstacle information in the blind area. The embodiment of the present invention makes up for the problem of a perception blind spot before the vehicle arrives at the intersection by acquiring the environmental information at the intersection, and improves the vehicle's ability to predict obstacles at the intersection.

Description

technical field [0001] The present invention relates to the technical field of automatic driving, in particular to a method and device for predicting the movement trajectory of an obstacle at an intersection. Background technique [0002] In the prior art, since the self-driving vehicle needs to rely on the perception of the surrounding environment to make trajectory planning, it is very important for the self-driving vehicle to fully perceive the obstacles around the self-driving vehicle. However, due to the limited perception range of autonomous driving vehicles, when passing through surrounding environments such as road intersections with a lot of concealment and occlusion, autonomous driving vehicles will have perception blind spots. When the self-driving vehicle cannot perceive the obstacles in the blind spot, it will not plan its own driving trajectory according to the obstacles in the blind spot. As a result, when the self-driving vehicle passes through the road inte...

AI Technical Summary

Problems solved by technology

As a result, when the self-driving vehicle passes through the road intersection, it cannot avoid the obstacles that suddenly appear in the blind area of ​​the intersection in time, which reduces the safety of the vehicle.

Images