Control method and control device of unmanned equipment

Abstract

The invention discloses a control method and control device for unmanned equipment, and the unmanned equipment can obtain a to-be-recognized image collected by the unmanned equipment, and determines the position of a target object in the to-be-recognized image from the to-be-recognized image. Then, according to the reference object information of the reference object in the preset electronic map and the acquisition position of the unmanned equipment when acquiring the to-be-identified image, the target reference object position of the target reference object involved in the to-be-identified image in the to-be-identified image is determined from the reference object. Then, the unmanned equipment can determine the position information of the target object in the real world according to the position of the target object, the position of the target reference object and the reference object information of the reference object, and control the unmanned equipment according to the determined position information of the target object in the real world; according to the invention, the position of the target object in the real world can be effectively determined, so that the driving safety ofthe unmanned equipment is ensured.

Description

technical field [0001] The present application relates to the field of unmanned driving, and in particular to a control method and control device for unmanned equipment. Background technique [0002] With the continuous development of information technology, unmanned driving technology will gradually enter various fields for application. [0003] In order to ensure the safe driving of unmanned equipment, it is usually necessary to collect images during unmanned driving and recognize the images to detect obstacles that may affect the driving of unmanned equipment. In the prior art, the image region corresponding to the obstacle in the image can be identified first, and then the distance of the obstacle relative to the unmanned driving device can be predicted through a pre-trained depth prediction model. However, in practical applications, it is necessary to obtain a large number of training samples to train the depth prediction model. Since there are many training samples, i...

AI Technical Summary

Problems solved by technology

However, in practical applications, it is necessary to obtain a large number of training samples to train the depth prediction model. Due to the large number of training samples, it takes a long time to train the depth prediction model.

Another way in the existing technology is to directly determine the distance between the obstacle and the unmanned device based on the image area of ​​the obstacle in the image, the parameters of the camera itself, and the height of the camera from the ground, and in some cases This method cannot effectively determine the distance between the unmanned equipment and obstacles

Images