Loopback detection method and device and storage medium

By building a historical local map in a mobile robot and registering it, the problem of no loopback or false detection in the existing loopback detection algorithm is solved, and the accuracy of loopback detection is improved.

CN119741347AActive Publication Date: 2025-04-01ZHEJIANG HUARAY TECH CO LTD
4 Cites 0 Cited by

Patent Information

Application Number
CN202411680217.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-21
Publication Date
2025-04-01
Estimated Expiration
2044-11-21

AI Technical Summary

Technical Problem

The existing loopback detection algorithms have problems in mobile robots that cannot detect loopbacks or false detection, which affects the operating effect of mobile robots.

Method used

By taking the environment-aware data frame currently collected by the environment-aware device as the current data frame, the historical data frame corresponding to the current data frame is obtained, a historical local map is constructed, and whether a loop occurs is determined through the registration results. The specific steps include selecting candidate data frames adjacent to the absolute pose. If the perceptual range difference is in the high difference threshold interval, selecting supplementary data frames with the perceptual range difference in the low difference threshold interval, and building a historical local map based on the candidates and supplementary data frames, and registering to determine loopbacks.

Benefits of technology

By adding historical data frames with more similar features to the current data frame, the accuracy of loopback detection is improved and the situation of false detection and missed detection is reduced.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a loopback detection method and device and a storage medium, and the method comprises the steps: selecting a historical data frame, the absolute pose of which is adjacent to the absolute pose corresponding to a current data frame, from a historical data frame set, and obtaining a candidate data frame; if the range difference between the sensing range of the candidate data frame and the sensing range of the current data frame is in a high difference threshold value interval, the candidate data frame is detected; if yes, selecting a historical data frame of which the acquisition time is adjacent to the acquisition time of the candidate data frame and the range difference between the sensing range and the sensing range of the current data frame is in a low difference threshold interval from the historical data frame set, and obtaining a supplementary data frame; according to the method, the candidate data frame and the supplementary data frame are combined to construct the historical local map, the current data frame and the historical local map are registered, whether loopback occurs or not is determined based on the registration result, the historical data frame with more similar features with the current data frame can be added, and loopback detection accuracy is improved.
Need to check novelty before this filing date? Find Prior Art