Automatic deviation correction control method and storage medium of magnetic guided AGV based on visual SLAM
Through visual SLAM technology and the improved ORB-SLAM2 system, the autonomous correction and automatic recovery of magnetically guided AGV in the case of demagnetization are achieved, and the automatic parking problem caused by AGV demagnetization is solved, and the efficiency of unmanned duty is improved.
CN114859924BActive Publication Date: 2025-03-28HEFEI UNIV OF TECH
2 Cites 0 Cited by
Patent Information
- Application Number
- CN202210521677.4
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-05-13
- Publication Date
- 2025-03-28
- Estimated Expiration
- 2042-05-13
AI Technical Summary
Technical Problem
The magnetically guided AGV may demagnetize during driving, resulting in automatic parking, requiring manual intervention to resume normal operation, affecting the unmanned duty of the railway traction substation.
Method used
Using the automatic deviation correction control method based on visual SLAM, a grid map is built through a Kinect V2 camera and the improved ORB-SLAM2 system, the demagnetization status of AGV is obtained in real time, and through visual SLAM navigation, the AGV automatically returns to the track and automatically resumes driving.
Benefits of technology
It realizes the autonomous correction and automatic recovery of AGV in demagnetization, reduces manual intervention, and improves the unmanned duty efficiency of railway traction substations.
✦ Generated by Eureka AI based on patent content.
Abstract
The present invention discloses an automatic deviation correction control method and storage medium for a magnetically guided AGV based on visual SLAM, the method comprising calibrating a Kinect V2 camera; the AGV is equipped with a Kinect V2 camera, and a grid map of the inspection environment is constructed based on an improved ORB‑SLAM2 system; the demagnetization state of the magnetically guided AGV is obtained; and the visual SLAM navigation deviation correction of the magnetically guided AGV is implemented based on the grid map, the information obtained in real time by the Kinect V2 camera, and the demagnetization state of the AGV. In the method of the present invention, after the AGV is demagnetized, the visual SLAM navigation is based on a known global map and is not restricted by the track laid by the magnetic strip. When the mobile platform leaves the magnetic strip track, it can still know its position, and use the position of the nearby magnetic strip in the map as the target point, autonomously navigate back to the track and adjust the posture, thereby reducing the human participation rate during the operation of the AGV and improving work efficiency.
Need to check novelty before this filing date? Find Prior Art