Trajectory prediction method, device and storage medium

Abstract

The embodiments of the present invention disclose a trajectory prediction method, a trajectory prediction device, and a storage medium. According to the embodiments of the present invention, the method includes the following steps that: the location information and driving characteristics of a first object are obtained; a region where the first object is located is determined according to the location information of the first object; driving scene classification is performed on the first object according to the region where the first object is located and the driving characteristics of the first object, so that the driving scene type of the first object is obtained; reference driving characteristics corresponding to the driving scene type are obtained; and a second object that matches thereference driving characteristics is determined from an object selection range corresponding to the first object; and the driving trajectory of the second object is predicted based on a driving path in which the second object is currently located and the driving characteristics of the second object. According to the trajectory prediction method, the trajectory prediction device, and the storage medium provided by the embodiments of the present invention, the second object that may collide with the first object is filtered out from the driving scene of the first object, and only the moving trajectory of the second object is predicted, and therefore, computational resource consumption can be reduced, and trajectory prediction efficiency can be improved.

Description

technical field [0001] The present application relates to the field of computers, and in particular to a trajectory prediction method, device and storage medium. Background technique [0002] With the popularization of intelligence, vehicles, ships, spacecraft, robots and other machinery can use the assistance of computer technology to avoid collision accidents and improve mobile efficiency. For example, in addition to distinguishing static obstacles around the own vehicle, the on-board computer can also predict the trajectory of dynamic obstacles around the own vehicle, and judge whether the dynamic obstacle poses a potential threat to the own vehicle based on the trajectory of the dynamic obstacle. security threat. [0003] However, current trajectory prediction methods require a lot of computing resources. Contents of the invention [0004] Embodiments of the present application provide a trajectory prediction method, device, and storage medium, which can reduce the c...

AI Technical Summary

Problems solved by technology

[0003] However, current trajectory prediction methods require a lot of computing resources

Images