Mobile robot repositioning method and device based on visual features and 3D laser
A mobile robot, visual feature technology, applied in the direction of instrumentation, image analysis, calculation, etc., can solve the problems of lost positioning, storage robot storage robot estimated pose information errors, etc., to achieve precise positioning, improve relocation accuracy, and realize positioning Effect
Pending Publication Date: 2022-08-05
HANGZHOU DIANZI UNIV
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Positioning information is the basis for the movement of storage robots. In recent years, the development of SLAM technology has made it possible for storage robots to locate autonomously. However, storage robots often encounter problems of lost positioning during actual operation. The specific manifestations are: internal or external abnormal reasons As a result, the storage robot is forced to restart, and the dynamic environment makes the storage robot estimate the pose information incorrectly, etc.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] The following is combined with the attachment description to further describe the execution steps of this method in detail, but the protection range of the present invention is not limited to the following.
[0040] like figure 1 It shows that the present invention proposes a method of mobile robot regulation based on visual characteristics and 3D laser, including the following steps:
[0041] The multi -line lidar used in the embodiment of the present invention is the Quanergy M8 series 16 -line laser radar. The left and right cameras use the USB camera after the calibration parameter. image 3 Show.
[0042] S1: Using multi -line lidar and IMU to build 3D maps at the actual scenario, adopt real -time correlation scanning matching, non -linear back -end optimization, branch -boundary acceleration return loop detection for 3D SLAM system map construction, obtaining mobile robots relative At the position of the Apriltag label, the Apriltag label world coordinate information i...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a method for repositioning a mobile robot and a device based on visual features and 3D laser. The method comprises the following steps: firstly, carrying out environment mapping and automatic calibration of world coordinates of an Apriltag; when the mobile robot loses positioning, a label detection function of the left camera and the right camera is started, and the mobile robot stops moving after labels are detected; the relative pose between the mobile robot and the label is obtained, filtering processing is carried out within a period of time, and the stability of pose data is guaranteed; the world coordinates of the robot are recovered according to the label world coordinates obtained through calibration, and preliminary repositioning is achieved; and carrying out directional range search by taking the world coordinate as a center, and continuously matching 3D point cloud frame data obtained by scanning with the existing sub-graph to realize accurate relocation. Therefore, the positioning capability of the mobile robot by using the multi-line laser radar SLAM is recovered, and the positioning capability of the mobile robot can be recovered at a relatively low cost in the actual operation process.
Description
Technical field [0001] The invention is a mobile robot regulating technology field, which is specifically involved a mobile robot regulating method and device based on visual characteristics and 3D laser. Background technique [0002] With the rapid development of the modern logistics storage industry, the use of mobile robots to replace manpower handling is gradually being carried out. More and more intelligent warehousing robots are stepping into the warehouse of the logistics industry to begin to undertake the task of autonomous transportation and further promote the logistics warehouse's warehouse. Unmanned and intelligent. The core issue of intelligent warehousing robots in actual scenarios is how to position, plan, and navigate the task according to the positioning information of the sensor and environmental information. Positioning information is the basis for the movement of warehousing robots. In recent years, the development of SLAM technology has made the independent p...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/73G06T7/80
CPCG06T7/74G06T7/80G06T2207/10028
Inventor 金建波林志赟王博韩志敏
Owner HANGZHOU DIANZI UNIV