Assembly operation data set construction system and method based on virtual-real combination

Abstract

The invention provides an assembly operation data set construction system and method based on virtuality and reality combination. The system comprises a real assembly operation device, a virtual assembly operation device, an operation part set and a virtuality and reality combination assembly operation data set construction method. The real assembly operation device comprises a six-degree-of-freedom mechanical arm, a handle, a six-dimensional force sensor and a mechanical gripper which are connected in sequence; the virtual assembly operation device comprises a seven-degree-of-freedom force feedback hand controller, a virtual mechanical arm, a virtual six-dimensional force sensor and a virtual mechanical gripper; the virtuality and reality combined assembly operation data set construction method comprises a space pose and operation force mapping method of real operation and virtual operation and an operation position, pose, force and torque data set generation method. According to the assembling operation data set construction system and method based on virtuality and reality combination, precise perception, flexible decision making and accurate control of a robot imitating and learning human hands can be achieved, and a high-quality and large-sample learning data set can be rapidly collected.

Description

technical field [0001] The present invention relates to interdisciplinary fields such as mechanics, robotics, instrument science, control science, computer science, sensor technology, human-computer interaction technology, virtual-real combination technology, etc., and relates to a system and method for constructing assembly operation data sets based on virtual-real combination. Background technique [0002] Artificial intelligence model training requires a large amount of high-quality data. If model training is carried out for on-site operation tasks, especially in some special environments such as high-risk environments and weightlessness, it is difficult to perform large-scale operations on dangerous targets and space non-cooperative targets in real environments. It is difficult to ensure the safety of operators when carrying out data collection experiments; if you want to build a simulation platform to obtain real data, you will face high experimental costs, and because t...

AI Technical Summary

Problems solved by technology

[0006] The technical problem to be solved by the present invention is that artificial intelligence model training requires a large amount of high-quality data. If the model training is carried out for on-site operation tasks, especially for some special environments such as high-risk environments and weightlessness, the operation tasks for dangerous targets and space non-cooperative targets, etc. , it is difficult to carry out a large number of data collection experiments

Images