SLAM method based on rodent model and WIFI fingerprint

Abstract

The invention discloses a SLAM method based on a rodent model and a WIFI fingerprint and relates to the field of bionics and wireless signal networks; a fingerprint recognition method based on WIFI signal strength is used; the WIFI fingerprint information is used for replacing local scene cellular network in the original rodent model; a location fingerprint database is established in an offline stage; a Bayesian algorithm is used for completing matching of WIFI signal strength fingerprint information in the online locating stage; the activity of the pose cellular network is corrected; finally,a more accurate experience map is obtained; and the SLAM method based on the rodent model and WIFI fingerprint in the present invention is adopted so that not only the locating accuracy of the mobilerobot is higher but also the stability of the system is improved and has good locating performance.

Description

technical field [0001] The invention relates to the field of bionics and wireless signal network, in particular to a SLAM method based on rodent model and WIFI fingerprint. Background technique [0002] Simultaneous localization and map construction are major challenges for mobile robots. Because the mobile robot is essentially a mobile sensor platform, although the types and capabilities of the sensors are different, there are widespread problems such as odometry drift and different noises. Later, after continuous exploration by scholars, bionic robots gradually highlighted good application prospects, showing perfect biological rationality and high adaptability to the natural environment. The most studied of these is the rodent model. [0003] This model integrates the path integral and visual scene information into the pose perception cell model, so that the mobile robot has a certain ability to update and predict, and at the same time establishes a history mapping algor...

AI Technical Summary

Problems solved by technology

[0003] This model integrates the path integral and visual scene information into the pose perception cell model, so that the mobile robot has a certain ability to update and predict, and at the same time establishes a history mapping algorithm for information such as time, spatial position and behavior, which has been widely used. In the positioning and navigation of the robot, many problems that are difficult to solve by SLAM have been solved. However, there are certain errors in the visual scene information obtained by the rodent model and the information of the distance measurement odometer. For the error of the visual odometer, FAB- MAP (fast appearance based mapping), a closed-loop detection algorithm based on a historical model, can improve the stability of the system through real-time key frame matching, but the positioning accuracy is not stable and the robustness is not strong

Therefore, a separate rodent model needs to be further improved in terms of positioning accuracy and robustness

Images