SLAM data association method based on fuzzy-self-adaptation

Abstract

An SLAM data association method based on fuzzy-self-adaption is disclosed and a fuzzy-self-adaptive data association method based on an error ellipse and an associated threshold value is provided for the deficiencies of an existing SLAM data association method. According to the SLAM data association method, a fuzzy logic rule is applied to data association of a feature observation value and an estimation value, and the threshold value can be adaptively determined according to variations of the environment and noises, so that the data association effect is improved; and in order to effectively prevent a false road sign, a minimum road sign interval in the environment is tracked according to observation data, one, serving as a new virtual road sign, of two observation road signs with a shortest Euclidean distance is added in a system taste, and in addition, data association is carried out on the other observation quantity and the virtual road sign by virtue of the fuzzy rule. A simulation experiment and a real experiment prove that the SLAM data association method is capable of solving the data association problem and well adapting to the variations of the environment and the noises, so that the virtual road sign is effectively prevented and the observation loss rate is reduced.

Description

technical field [0001] The fuzzy-adaptive SLAM data association method applies fuzzy logic rules to the data association of characteristic observations and estimated values, and can adaptively determine the threshold according to changes in the environment and noise, thereby improving the effect of data association, and then synchronously Improving the correlation accuracy and positioning accuracy in positioning and map construction belongs to the field of robot autonomous navigation. Background technique [0002] The basic idea of ​​Simultaneous Localization and Mapping (SLAM) is to let the robot move from an unknown position in an unknown environment, estimate its own position through the information of the landmark points scanned by its own sensor, and build an augmented reality map at the same time. Quantitative map. In the SLAM process, real-time map estimation and updating are performed based on observation information, and data association is a key issue. Data assoc...

AI Technical Summary

Problems solved by technology

But a lower association threshold will result in a higher observation drop rate

Therefore, when factors such as landmark distribution and system noise change, the observation discard rate will increase, resulting in a decrease in SLAM estimation performance.

[0006] (2) In a complex environment with large uncertainties, the accuracy of the association needs to be improved

The above methods cannot effectively prevent false landmarks, especially in the case of sparse landmarks in the environment, identifying one landmark as two landmarks, resulting in the distribution of the observation data of this landmark between the two, so that the observation is of great importance to the mobile robot. The effect of pose correction is weakened

Images