Auxiliary positioning method, device, robot and computer-readable storage medium

Abstract

The invention relates to an auxiliary positioning method and device, a robot and a computer readable storage medium. The robot collects WIFI information transmitted by multiple WIFI transmitters in the environment in real time through a WIFI receiver; when determining that the number of the currently acquired WIFI identifiers is greater than or equal to a number threshold value and when the WIFI information is acquired and the original global positioning mode fails, the mode for global positioning is switched, the currently acquired WIFI information is input into a pre-trained network model, and the position corresponding to the maximum probability value predicted by the network model is determined as the current position. Namely, when the reliability of the original global positioning mode is low, WIFI is adopted for auxiliary positioning. Due to the fact that the reliability of an original global positioning mode at the current moment is low, the reliability of WIFI adopted for positioning at the moment is higher than that of the original global positioning mode at the current moment, and therefore the error rate of the robot during global positioning can be reduced.

Description

technical field [0001] The present application belongs to the field of positioning, and in particular relates to an auxiliary positioning method, device, robot and computer-readable storage medium. Background technique [0002] As technology advances, robots are able to operate autonomously or semi-autonomously. [0003] Because the working environment of the robot is subject to many external influences and interferences, the working environment is relatively complex and the working environment changes at any time, so if the robot is to complete the navigation task autonomously in the indoor environment, the robot needs to be able to clearly understand its global position in the environment , that is, the robot can perform global positioning autonomously. Global positioning means that the robot uses its own sensors (such as laser emitters, cameras, etc.) to perceive information to determine the pose without any prior knowledge of the initial pose (entered into the robot in ...

AI Technical Summary

Problems solved by technology

However, the existing global positioning algorithms have certain defects.

For example, when the map is large, the particle filter algorithm based on the Monte Carlo algorithm needs to generate a relatively large number of particles, resulting in a large amount of calculation, which is not conducive to accurate positioning. In addition, the particles generated by the algorithm cannot completely cover the robot. The map at the place will cause the positioning accuracy to decrease

Monocular vision needs to use a vision system for positioning, which will increase the cost and calculation burden of the robot. In addition, if the processed image is more complex, the calculation pressure will be further increased, resulting in a decrease in positioning accuracy.

[0005] When the global positioning accuracy at certain moments is too low, the reliability of the positioning results obtained by the robot will be low, which will eventually lead to global positioning errors

Images