Font Size: a A A

Design And Implementation Of Mobile Robot Control System

Posted on:2019-08-13Degree:MasterType:Thesis
Country:ChinaCandidate:X LiFull Text:PDF
GTID:2428330548476293Subject:Electronics and Communications Engineering
Abstract/Summary:PDF Full Text Request
In China,which is an industrial power,the social reality of the aging population,high labor costs and low demographic dividend have received more and more attentions.Therefore,the logistics,warehousing and other industries are facing huge challenges.With the policy of "Industry 4.0" and "Made in China 2025",industrial robots have been developing rapidly,especially for mobile robots.Taking the third generation mobile robot as the background,the goal of the research is moving mobile robot to the target location and grasping or carrying the target object.Hence,the control system of mobile robot is designed in this paper.Specifcally,the domestic and foreign development,future trends and related technologies are analyzed and introduced in this paper.Then,according to the index of system function and the actual demand of the project,a mobile robot control platform is designed and built.And the selection of visual sensor,core processor,the platform of robot,the design scheme of control and navigation are included.What's more,the visual navigation of mobile robot is the focus of the research,including the design of visual perception system and target tracking algorithm.The visual perception system is designed to carry out the collection of environmental information,such as the data of depth image and color image.At the same time,for the calibration of vision system,the internal and external parameters of color cameras and deep cameras,as well as the rotation and translation matrixes between the two cameras,respectively are obtained through Zhang's calibration method.On the basis of this,the color image data and the depth image data are matched to obtain the 3D information of the environment.For the target tracking process,an improved fusion algorithm of Camshift and perceptual hash is proposed in this paper,to obtain the centroid of the corresponding template target and the 3D coordinates of the centroid with the 3D information of the environment.Then,the design of the system communication protocol and the robot control instruction,the implementation of the system software are realized.In the VS2012,combined with MFC,Open CV,Kinect SDK and PCL point cloud library,the visual navigation unit is designed to complete the target tracking algorithm,the 3D information acquisition algorithm and the realization of the PC man-machine interface.At the same time,the software of robot control unit is designed through the corresponding control instruction.Finally,the developed control system of mobile robot has been repeatedly debugged and tested.Furthermore,the experiments on target tracking and the 3D coordinate acquisition of template target are carried out.And the experimental data show that the system vision navigation unit can meet the requirements of mobile robot control system basically.What's more,dynamic experiments are carried out to complete the requirements for the movement of the mobile robot to the target position,and the capture and handling of target object.
Keywords/Search Tags:Target tracking, Mobile robot, Industrial robot, Depth, 3D information, Kinect 2.0
PDF Full Text Request
Related items