Target attitude deep learning tracking acquisition method, learning system and storage medium

Abstract

The present invention relates to the technical field of robots, and discloses a deep learning and tracking collection method based on a target posture, a learning system and a storage medium for controlling robot learning and teaching actions, wherein the deep learning tracking collection method based on a target posture includes the following steps: selecting the A plurality of reference points of the teaching action, respectively tracking the movement of each of the reference points and recording the teaching tracking data; analyzing each of the teaching tracking data, and fitting at least two functions through the relationship between movement and time: used to describe an attitude function of the change of the target attitude over time, a displacement function used to describe the change of the target position over time; a control program is generated so that the robot can realize the teaching according to the attitude function and the displacement function action. The invention generates a driver program by collecting the teaching action of the target, reduces the degree of demand for manual participation, and has the advantages of high intelligence, high degree of imitation and reduction, and the like.

Description

technical field [0001] The present invention relates to the technical field of robots, and in particular to a tracking acquisition method, a learning system and a storage medium based on deep learning of target posture. Background technique [0002] A robot (Robot) is a high-tech product with a preset program or principled program inside. After receiving a signal or instruction, it can judge and take actions to a certain extent, such as moving, picking up, and swinging limbs. The task of the robot is mainly to assist or even replace the work of humans in some occasions. The actions and information judgments involved in the actual work scene are often very complicated, and it is difficult to record them all in the robot in the form of a program in advance. Knowledge, self-learning to improve adaptability and intelligence level, that is, robot learning, has become a very hot research focus in the robot industry. [0003] In the prior art, the process of the robot simulating t...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a deep learning tracking acquisition method based on target posture, a learning system and a storage medium, aiming to solve the problem of low degree of motion restoration, large amount of calculation for taking points, and manual labor when robots in the prior art simulate human teaching actions. The problem of more participation and less intelligence

Images