Indoor robot navigation method based on environment characteristic detection

Abstract

The invention provides an indoor robot navigation method based on environment characteristic detection, and aims to solve the problem that navigation semantic information is insufficient in positioning and is low in intelligence degree at present. The method comprises the following steps that: training an object detection model on a robot end, and establishing a semantic map which combines an indoor grid map with an object position; enabling a robot to rotate for one circle on the spot, utilizing the object detection model to identify an observed object, and utilizing a maximum likelihood estimation method to solve the global pose of the robot; and subscribing for the voice result topic of a remote control end by the robot end, carrying out mapping matching on an obtained voice result anda semantic dictionary in the semantic map, identifying a destination position to be navigated, and utilizing a center line in a corridor to plan the global path by the robot end. By use of the method,the problem that initial positioning can not be carried out in a traditional method is solved, the method is efficient and accurate in positioning, the planned path can more conform to the perceptionof the robot for an unknown environment so as to be safe, and realized semantic navigation can be more conveniently integrated in a robot product.

Description

technical field [0001] The invention belongs to the field of robot navigation, and relates to object detection technology, positioning navigation technology, central line path planning technology and the like. Background technique [0002] Localization is the premise and basis for mobile robots to carry out various navigation tasks. According to different task stages, positioning can be divided into global positioning and pose tracking. Global positioning refers to automatically calculating its own pose in the global map through its own sensors and algorithms without knowing the initial pose; Map, calculate the pose of the next cycle. [0003] Due to the lack of prior pose information for global positioning, the required observation information is more important. Therefore, it is often difficult to achieve autonomous global positioning due to the lack of semantic information of point cloud data observed by lidar. Most current global positioning algorithms are based on Vis...

AI Technical Summary

Problems solved by technology

[0024] Aiming at the problem of insufficient semantic information and low intelligence of the current positioning and navigation, the present invention provides an indoor robot navigation method based on environmental feature detection. By establishing a semantic map, the positioning and navigation method has higher semantic information and achieves Accurate positioning and high-semantic navigation effects have the advantages of high precision, simplicity and effectiveness, and have high significance for the product application of robot positioning and navigation

Images