Positioning method and device, intelligent robot and computer readable storage medium

Abstract

The invention discloses a positioning method. The positioning method is applied to an intelligent robot and is characterized in that a plurality of sensors used for detecting the detection poses of the intelligent robot are installed on the intelligent robot, the sensors comprise laser sensors, the positioning method comprises the steps of obtaining a plurality of detection data detected by the sensors during detection of the detection poses, wherein the laser sensors are used for detecting the laser data; calculating the adaptive confidence of the laser data on at least one degree of freedomaccording to the laser data; calculating an adaptive weight of the pose constraint of the at least one piece of detection data in a graph optimization model according to the adaptive confidence; constructing a graph optimization model and a target function of the graph optimization model according to the at least one piece of detection data and the adaptive weight; and calculating the optimized pose of the intelligent robot according to a target function. The invention further discloses a positioning device, an intelligent robot and a computer readable storage medium.

Description

technical field [0001] The present application relates to the field of robot technology, and more specifically, to a positioning method and device, an intelligent robot, and a computer-readable storage medium. Background technique [0002] Intelligent robot positioning algorithms usually use a filter framework to construct motion equations and observation equations, and combine odometer data and laser matching to achieve pose estimation. However, when the surrounding environment of the intelligent robot changes drastically or the laser data does not return data obviously, the observation equation will have a large error, resulting in an error in the pose estimation. At the same time, when the system has more reference sensor data, the filter algorithm cannot perform deep fusion on these data. This makes the robot unable to work in a more complex environment, which may easily cause the positioning of the intelligent robot to drift and easily lead to the loss of the intellige...

AI Technical Summary

Problems solved by technology

However, when the surrounding environment of the intelligent robot changes drastically or the laser data does not return the data obviously, the observation equation will have a large error, resulting in an error in the pose estimation.

At the same time, when the system has more reference sensor data, the filter algorithm cannot perform deep fusion of these data

It makes the robot unable to work in a more complex environment, which may easily cause the positioning of the intelligent robot to drift and easily lead to the loss of the intelligent robot

Images