Robot navigation method based on machine vision and machine learning

Abstract

The invention discloses a robot navigation method, comprising robot imitation learning and autonomous navigation steps. The robot imitation learning step comprises: recording each frame video image obtained by a camera and corresponding control commands; extracting a visual feature vector corresponding to each frame video image; employing the visual feature vectors and control commands as a training data set of a classifier; and calculating an optimal vector of the classifier. The robot autonomous navigation step comprises: extracting the visual feature vector of each frame video image; and the classifier calculating and outputting the control commands according to the visual feature vectors of the video images and the optimal vectors to realize autonomous navigation. The method does not need to establish complex environment models or robot motion control models; robot detection to environments mainly depends on visual feature information, and is suitable for indoor navigation and outdoor navigation; the method can be applied to mobile robots, humanoid robots, mechanical arms, unmanned aerial vehicles, etc.

Description

technical field [0001] The invention belongs to the field of robots, and relates to robot motion control, robot indoor and outdoor navigation and computer technology, in particular to a robot navigation method based on machine vision and machine learning. Background technique [0002] With the continuous development of robotics technology, intelligent mobile robots have entered various fields of social life, playing an increasingly important role in household services, medical services, shopping malls, industry, agriculture and military fields. Demand is also increasing day by day. As a basic problem in the research of intelligent mobile robots, autonomous navigation has become a key technology for mobile robots to achieve autonomy and intelligence. [0003] In recent years, many mobile robot platforms have emerged one after another, and their performance is also very superior. A large number of theoretical and applied researches have been carried out in combination with s...

AI Technical Summary

Problems solved by technology

However, because these technologies are highly dependent on the configuration, environment, and parameter settings of the robot, they cannot be applied to most mobile robots.

[0004] The robot navigation environment is relatively complex. The existing navigation methods are mainly aimed at specific environments, certain robot configurations (robots are equipped with binocular vision, trinocular vision, panoramic cameras, laser radar and other sensors), simple dynamic environments, etc., and most The experiments are mainly verified by simulation

Due to the different mechanical structures and hardware configurations of robots, and the complex and changeable environment, various navigation methods are generally only effective for specific environments. So far, there is no general navigation method applicable to different environments.

Images