Autonomous mobile robot self-supervised learning and navigation method based on generative adversarial network

Abstract

The invention belongs to the field of robot learning, and relates to an autonomous mobile robot self-supervised learning and navigation method based on a generative adversarial network. The method comprises the following steps: firstly, setting action training times K of the robot; then the robot collecting a state image of the environment; the robot calculating a loss function between the state image and the predicted image at the previous moment, and then calculating a reward and punishment signal according to the loss function; updating the prediction network weight; repeating the steps of acquiring the image by the robot, predicting the action and executing the action until the Kth time is reached; and finally, weighting all reward and punishment signals, and updating the prediction network weight. Therefore, the problem of how to autonomously supervise learning of the robot is solved, and the workload of manual marking and manual intervention is reduced to a great extent.

Description

technical field [0001] The invention relates to the field of robot learning, in particular to a self-supervised learning and navigation method for an autonomous mobile robot based on a confrontation generation network. Background technique [0002] Autonomous mobile robots are widely used in many fields such as production and life, and the scenarios they face are becoming more and more complex. Traditional methods require a large amount of manually labeled image data for the robot's deep neural network to learn about the relevant data. The SLAM (Synchronous Localization and Mapping) method needs to continuously measure the relative position and angle of the robot and the target. These targets also need to be manually marked and screened. It is difficult to find such a suitable target in many practical tasks; and the traditional convolutional neural network The network needs to normalize the data set, different sizes are mixed together and it is difficult to train, and the t...

AI Technical Summary

Problems solved by technology

[0003] Therefore, the technical problem to be solved by the present invention is to overcome the shortcomings of the self-supervised learning environment of autonomous mobile robots in the prior art and to make up for the defects of large manual labeling workload, thereby providing a self-supervised learning of autonomous mobile robots based on adversarial generative networks and navigation method

It solves the problems of autonomous mobile robots learning environmental information, autonomous navigation and manual labeling workload

Images