Intelligent robot grabbing method based on action demonstration teaching

Abstract

The invention discloses an intelligent robot grabbing method based on action demonstration teaching, and relates to the technical field of robot learning. The method comprises the following steps thatthe hardware environment building of an action demonstration teaching programming system is completed; a person demonstrates the grabbing operation to form a human teaching action video, and the person uses a demonstrator to control a robot to complete the demonstrating grabbing action to form a robot teaching action video; data of human and robot teaching action videos are gathered to be subjected to denoising and expanding operation; a meta-learning algorithm is adopted to directly and automatically learn priori knowledge from teaching actions of human and the robot so as to realize learning of new tasks. According to the meta-learning algorithm provided by the intelligent robot grabbing method based on the action demonstration teaching, one-eye learning of imitation learning can be realized in different background environments, different human demonstrators and different robots, and learning of an adaptive target loss function is realized by using time convolution, so that the network can capture multiple frames of human action image information at the same time; and the method has strong adaptability and robustness.

Description

technical field [0001] The invention relates to the technical field of robot learning, in particular to an intelligent robot grasping method based on action demonstration and teaching. Background technique [0002] In recent years, robotic automation systems have developed rapidly and are widely used in industrial and household environments. They have played an important role in solving the problem of social aging and accelerating industrial upgrading and transformation. Among them, robot grasping technology is an important part of robot automation system, which involves almost all applications related to robot operation, such as industrial robot sorting and handling, household robot desktop cleaning, etc. However, most of the current mature grasping systems are designed around a structured operating environment, relying on the pre-acquired target model information to plan the grasping process, the grasping target is single and the application scenarios are relatively fixed,...

AI Technical Summary

Problems solved by technology

However, when using traditional machine learning methods to grasp unknown objects, manual design of features is time-consuming and laborious, and relies heavily on human experience. The quality of features directly affects the performance of the algorithm. The grasping system has poor generalization ability and is difficult to transfer only for the current task. to problems in other tasks

Images