SLAM data association method based on adaptive local and grouping association strategy

Abstract

The invention provides an SLAM data association method based on a self-adaptive local and grouping association strategy. The method comprises the following specific steps: firstly, adaptively determining a local data association region according to the position of the mobile robot at the current moment, the measurement range of a sensor and the distribution condition of observation values at the current moment; secondly, adaptively determining the grouping number of the observation values according to the local association region and the number and distribution of the current observation values, and grouping the current observation values by using a Gaussian mixture clustering algorithm on the basis of the grouping number; thirdly, completing data association between the observed value ineach group and the feature points in the local area by using a joint compatible branch and bound algorithm, and screening out an optimal association solution of each group; and finally, integrating each group of optimal solutions to obtain a final data association result. Experimental results prove that the method can reduce the association calculation amount while ensuring high association accuracy.

Description

technical field [0001] The invention belongs to the field of autonomous navigation of mobile robots, in particular to a SLAM data association method based on an adaptive local and group association strategy. Background technique [0002] Simultaneous localization and mapping (SLAM) is the key to autonomous navigation of mobile robots. The scheme was first proposed by Smith et al. in 1986. Specifically, the mobile robot uses its own sensors (such as depth cameras, laser range finders, sonar, etc.) A map of the surrounding environment, and at the same time use the built map to estimate its own pose. [0003] Data association is a difficult point in the SLAM problem, which means that the mobile robot matches the observation value of the sensor at the current moment with the features in the known local map, so as to determine whether the observation value corresponds to a known feature or a new feature. Wrong data association will lead to deviations in mapping and positioning,...

AI Technical Summary

Problems solved by technology

However, the calculation amount of the algorithm is exponentially related to the number of observations, which leads to poor real-time performance of the algorithm, and this problem is more serious in multi-feature environments

The mainstream SLAM data association algorithm cannot achieve high association accuracy and low association time at the same time, resulting in poor practical application of mobile robots

Images