A method, device and storage medium for controlling virtual object movement

Abstract

The embodiments of the present application relate to the field of artificial intelligence, and provide a method, device, and storage medium for controlling movement of a virtual object. The method includes: acquiring a pathfinding task of the virtual object and acquiring key points of the virtual object in a first pathfinding map set; the pathfinding task includes a pathfinding path of at least one partial map, and the keypoints in the keypoint set are the positions of the virtual object that conform to the preset movement behavior during the movement of the target path; obtain the virtual object in the first pathfinding map According to the set of key points and the real-time position, the virtual object is controlled to move from the real-time position to the target key point in the first path-finding map according to the path-finding task, and move to the next key point within the effective range of the target key point. , until the pathfinding task is completed. This solution can change the perspective of the game character at any time, infer the position of the game character from the local map, and make the game character move according to a relatively fixed path.

Description

technical field [0001] The embodiments of the present application relate to the technical field of artificial intelligence, and in particular, to a method, a device, and a storage medium for controlling movement of a virtual object. Background technique [0002] In the game industry, game testing can be implemented based on artificial intelligence (Artificial Intelligence, AI) technology. At present, the position of the game character is mainly identified by the following methods: [0003] In the game AI scheme that sets the route based on the global game map, the position of the game character in the global game map is identified by color, and then the path of the game character moving in the global game map is manually pre-set, that is, the manual marking is performed first. key points on the path, and then control the game character to move along the position of the key points on the path to complete the game test of the game character. Although the position of the game...

AI Technical Summary

Problems solved by technology

Although it is possible to identify the position of game characters in the complete game map by color, and does not need to manually record samples, the basis for its use is that the game image contains complete game map information, because most of the current gunfight games only have partial radar maps information, and the player cannot change the angle of view of the game character. Therefore, it is impossible to record the game image and game action of any angle. Therefore, it is difficult and not comprehensive enough to obtain the game image containing the complete game map, and it is difficult to obtain the game character in the game. An accurate location on the global game map will eventually lead to a reduction in the efficiency of the entire game test and an incomplete test effect

Images