Vision-based modular platform relative pose estimation system

A relative pose, modular technology, applied in computing, image analysis, instruments, etc., can solve problems such as large error in attitude information estimation, failure to build a multi-module relative pose system, and failure to build a relative pose system. , to achieve the effect of simple module, improving relative pose estimation ability, and solving target loss

Pending Publication Date: 2022-01-28
SHANDONG UNIV
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] 1) It is not suitable for modular robot platforms with multiple mobile platforms, and a relative pose system with multiple modules cannot be built;
[0009] 2) Robot pose estimation is acceptable for position information estimation, but the error value of pose information estimation is relatively large; 3) Only for pose estimation between two modules, there is no relative pose system for the overall modular platform

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Vision-based modular platform relative pose estimation system
  • Vision-based modular platform relative pose estimation system
  • Vision-based modular platform relative pose estimation system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] The modularized platform in the present invention is made up of 4 identical four-wheel mobile robots, adopts the mode of four-wheel differential steering, and is a four-wheel differential steering mobile robot. Each mobile platform (four-wheeled mobile robot) has a camera on the front and right side respectively, and double QR code targets for pose detection on the back and left side respectively. like figure 1 , taking two four-wheel differential steering mobile robots as an example, a 300mm×300mm square box is placed on them to place industrial cameras and dual QR code target modules. The dual QR code target modules are as follows: figure 2 As shown, it consists of two 80mm×80mm two-dimensional codes. Each two-dimensional code represents a different number and can be detected by the ROS node respectively. The distance between the two two-dimensional code targets is 80mm. Encoders are set on the left and right wheels of each four-wheeled mobile robot to obtain the ro...

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

No PUM Login to view more

Abstract

The invention discloses a vision-based modular platform relative pose estimation system, which comprises a master controller, an upper computer, a controller, a driver, an encoder and a camera; the front face and the right side face of each mobile robot are each provided with a camera, and the rear face and the left side face of each mobile robot are each provided with a double-two-dimensional-code target used for pose detection. Encoders are arranged on a left wheel and a right wheel of each mobile robot, each mobile robot corresponds to one set of upper computer, controller and driver, the controller is connected with the upper computer, the driver is connected with the controller, the camera is connected with the upper computer, and each upper computer is connected with the master controller. According to the system, the estimation capability of the relative pose between modular robot platforms is improved, the system is simple and low in cost, the real-time performance of pose estimation is good, the accuracy of pose estimation is ensured, the estimation of the relative pose between robots with partial incomplete or inaccurate information is realized, and the problem of target loss caused by visual detection is solved to a certain extent.

Description

technical field [0001] The invention relates to a system for obtaining overall relative pose information of a modular platform by means of a camera, and belongs to the technical field of positioning of the modular platform. Background technique [0002] Modular robot platform refers to multiple mobile platforms with different functions, which can change its configuration autonomously without human participation according to the changing requirements of the working environment to adapt to the new working environment. In a modular system, in order to ensure the operating range and variable configuration capability of the modular platform, it is necessary to obtain the relative pose information between the robot modules, and at the same time ensure the real-time performance of the relative pose information between the robot modules, so that the control system can make each The module smoothly enters the predetermined function area of ​​the platform to realize various functions ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/73G06F17/11
CPCG06T7/73G06F17/11
Inventor 周乐来黄双发李贻斌荣学文柴汇
Owner SHANDONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products