Method, device and electronic device for obtaining environment recognition model and control decision

Abstract

The present application relates to the technical field of robot deep learning models, and provides a method, device and electronic device for obtaining an environment recognition model and control decision-making. The method for obtaining an environment recognition model includes: obtaining an actual data information set and a simulation data information set of a robot; Based on the OPC UA information model, a plurality of the actual data information is converted into a plurality of first nodes, a plurality of the simulation data information is converted into a plurality of second nodes, and by calculating the relationship between the first node and the second node The correlation value of the actual data information set and the simulation data information set are fused to obtain the fusion data information set; the fusion data information set is used as the training set of the environment recognition model, and the Identify the model for training. The training sample of the present invention is large and has high reliability.

Description

technical field [0001] The present application relates to the technical field of deep learning models, and in particular, to a method, apparatus and electronic device for obtaining an environment recognition model and control decision. Background technique [0002] The existing robot environment recognition model is to perform self-supervised training on actual data information or simulated data information through the existing self-supervised model. The actual data information refers to the data information collected by the sensors installed on the robot. , the simulation data information refers to the data information generated on the simulation platform or simulation software to simulate the actual operation of the robot. [0003] However, the types of data currently used for self-supervised model learning are not perfect, the self-supervised model cannot quickly adapt to the new environment, and the reliability is not high; there is a lack of methods to fuse actual data ...

AI Technical Summary

Problems solved by technology

[0003] However, the types of data currently used for self-supervised model learning are not perfect, the self-supervised model cannot quickly adapt to the new environment, and the reliability is not high; there is a lack of methods to fuse actual data information and simulation data information as a training set

[0004] Based on the above problems, there is currently no effective solution

Images