[1]雷 程,孙立宁,陈国栋.基于Kinect的全向移动平台视觉伺服控制研究[J].机械与电子,2018,(08):61-65,70.
　LEI Cheng,SUN Lining,CHEN Guodong.Research on Visual Servo Control of Omnidirectional Mobile Platform Based on Kinect[J].Machinery & Electronics,2018,(08):61-65,70.
点击复制

基于Kinect的全向移动平台视觉伺服控制研究
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2018年08期
页码:
61-65,70
栏目:
智能工程
出版日期:
2018-08-24

文章信息/Info

Title:
Research on Visual Servo Control of Omnidirectional Mobile Platform Based on Kinect
文章编号:
1001-2257(2018)08-0061-05
作者:
雷 程1; 孙立宁1; 陈国栋2
(1.哈尔滨工业大学机电工程学院,黑龙江 哈尔滨 150001; 2.苏州大学机电工程学院,江苏 苏州 215006)
Author(s):
LEI Cheng1; SUN Lining1; CHEN Guodong2
(1.School of Mechatronics Engineering, Harbin Institute of Technology, Harbin 150001, China; 2.School of Mechanical and Electric Engineering,Soochow University,Suzhou 215006,China)
关键词:
全向移动平台;  视觉伺服控制;  Kinect相机;  人体跟踪;  交互控制
Keywords:
omnidirectional mobile platform;  visual servo control;  Kinect;  human tracking;  Interactive control
分类号:
TP242.62
文献标志码:
A
摘要:
针对移动机器人的交互控制进行研究,利用Kinect相机获取的人体特征点信息用于全向移动平台的视觉伺服控制中。首先,对完整约束下的移动平台构型进行设计,构建平台的正逆运动学模型; 其次,分析基于图像的视觉伺服控制模型,得到图像空间中特征点与笛卡尔空间平台的运动关系; 再次,对伺服控制系统进行设计,提出交互中特征点的提取及选取方式,给出雅可比矩阵的深度值估计方法,讨论偏差的增益值组合对平台运动的影响; 最后,选择符合条件的一组增益值对上述控制算法进行仿真,分析仿真结果,验证了控制算法的可行性。
Abstract:
In this paper, the interactive control of mobile robot is studied, and the information of human feature points acquired by Kinect camera is used in the visual servo control of omnidirectional mobile platform. Firstly, the mobile platform configuration under the complete constraint was designed, and the kinematics model of the platform was constructed. Secondly, the image-based visual servo control model was analyzed to obtain the motion relationship between the feature points in the image space and the platform in Cartesian space. Thirdly, the servo control system was designed, and the method of extracting and selecting feature points in interaction was proposed. Next, the depth value estimation method of Jacobian matrix was given, and the influence of the combination of the gain values on the motion of the platform was discussed. Finally, a set of gain values that conform to the conditions was selected to simulate the above control algorithm, and the simulation results were analyzed to verify the feasibility of the control algorithm.

参考文献/References:

[1] 王国胜, 夏凡, 吕强, 等. 基于动力学与运动学的四轮全向移动机器人轨迹跟踪控制[J]. 装甲兵工程学院学报, 2015(1): 54-59.
[2] 张鹏. 基于 ROS 的全向移动机器人系统设计与实现[D]. 合肥:中国科学技术大学, 2017.
[3] 孙强, 王文涛, 周璇. 基于 Kinect 传感器的全方位运输平台控制系统研究[J]. 电子设计工程, 2015(24): 99-102.(■
[4] 徐军, 孟月霞, 王天伦, 等. 基于 Kinect 的仿人机器人控制系统[J]. 传感器与微系统, 2017, 36(9): 97-100.
[5] CHEN J, WANG G, HU X, et al. Lower-body control of humanoid robot NAO via Kinect[J]. Multimedia Tools and Applications, 2018:77(55)1-16.
[6] YANG L, YANG B, DONG H, et al. 3-D markerless tracking of human gait by geometric trilateration of multiple Kinects[J]. IEEE Systems Journal, 2016(99):1-11.
[7] DU Y C, SHIH C B, FAN S C, et al. An IMU-compensated skeletal tracking system using Kinect for the upper limb[J]. Microsystem Technologies, 2018: 1-11.
[8] SCANO A, CHIAVENNA A, MALOSIO M, et al. Kinect V2 implementation and testing of the reaching performance scale for motor evaluation of patients with neurological impairment[J]. Medical engineering & physics, 2018, 56: 54-58.
[9] CORKE P. Robotics, vision and control: Fundamental algorithms in MATLAB Rsecond, completely revised[M]. Berlin:Springer, 2017.

备注/Memo

备注/Memo:
收稿日期:2018-06-01
作者简介:雷 程(1994- ),男,黑龙江绥化人,硕士,研究方向为视觉伺服控制技术; 孙立宁(1964- ),男,江苏苏州人,博士,教授,研究方向为机器人技术; 陈国栋(1983- ),男,山东济宁人,博士,副教授,研究方向为机器视觉技术。
更新日期/Last Update: 2018-08-24