Robot Chinese character writing learning method based on track imitation

Abstract

The invention relates to a Chinese character writing learning method based on track imitation, wherein the method belongs to the fields of artificial intelligent and robot learning. According to the method, imitation learning based on track matching is introduced into studying of a robot writing skill; demonstration data are coded through a Gaussian mixture model; track characteristics are extracted; data reconstruction is performed through Gaussian mixture regression; a generalized output of the track is obtained; and furthermore learning of a track-continuous Chinese character writing skill can be realized. An interference problem in the writing process is processed in a method of multiple demonstrations, and noise tolerance of the method is improved. According to the method, multitask expansion is based on the basic Gaussian mixture model; a complicated Chinese character is divided into a plurality of parts; track coding and reconstruction are performed on each divided part; and the method is applied for generating discrete tracks, thereby realizing writing of track-discontinuous Chinese characters. The Chinese character writing learning method realizes high Chinese character writing generalization effect.

Description

technical field [0001] The invention belongs to the field of artificial intelligence and robot learning, and in particular relates to the realization of trajectory matching-based imitation learning in robot writing skills, that is, a trajectory-based imitation-based Chinese character writing learning method. Background technique [0002] With the continuous development of robot research, its motion behavior is becoming more and more complex. For complex motions that are not easy to obtain, such as Chinese character writing tasks, traditional algorithms are implemented, that is, experienced "experts" acquire motor skills through underlying motion control. , becomes increasingly difficult, if not impossible. At this time, the robot needs to have the ability to learn and improve its intelligence so that it can find effective control strategies to complete complex motion tasks when traditional methods are difficult or impossible to achieve. [0003] Imitation learning is a way ...

AI Technical Summary

Problems solved by technology

Writing is a movement of complex trajectories, and there are two problems in its learning process: (1) representation of continuous complex trajectories; (2) generation of discrete trajectories

Existing methods, such as low-level motion control, control graph models, and recurrent neural networks, can be used to acquire writing skills, but none of them can effectively solve the above problems. Traditional control is more complicated, and its generalization performance is insufficient, so it cannot be transplanted. Control graph models Can generate discrete trajectories, but the ability to represent complex trajectories is insufficient, and recurrent neural networks can only be used for the reproduction of simple trajectories

Images