基于扩展图像特征的无标定视觉伺服方法

doi:10.16182/j.issn1004731x.joss.23-1593

系统仿真学报 ›› 2025, Vol. 37 ›› Issue (5): 1210-1221.doi: 10.16182/j.issn1004731x.joss.23-1593

基于扩展图像特征的无标定视觉伺服方法

张淑珍¹, 成煜坤¹, 刘杨波¹, 查富生²

^1.兰州理工大学机电工程学院，甘肃兰州 730050
^2.哈尔滨工业大学机器人技术与系统国家重点实验室，黑龙江哈尔滨 150001

收稿日期:2023-12-28 修回日期:2024-03-19 出版日期:2025-05-20 发布日期:2025-05-23
通讯作者: 成煜坤
第一作者简介:张淑珍(1969-)，女，副教授，博士，研究方向为特种机器人、智能工业机器人等。
基金资助:
国家自然科学基金(52265065);国家重点研发计划(2020YFB13134)

An Extended Image Features Based Uncalibrated Visual Servoing Method

Zhang Shuzhen¹, Cheng Yukun¹, Liu Yangbo¹, Zha Fusheng²

^1.School of Electrical and Mechanical Engineering, Lanzhou University of Technology, Lanzhou 730050, China
^2.State Key Laboratory of Robotics and System, Harbin Institute of Technology, Harbin 150001, China

Received:2023-12-28 Revised:2024-03-19 Online:2025-05-20 Published:2025-05-23
Contact: Cheng Yukun

摘要/Abstract

摘要：

针对传统无标定视觉伺服依赖图像雅可比矩阵的估计、相机各自由度运动耦合的问题，在基于图像的无标定视觉伺服的基础上，提出了一种基于扩展图像特征的无标定视觉伺服方法。通过分析视觉伺服过程中图像特征和相机位姿变化关系，将图像空间中视觉伺服过程分解为平移、拉伸、旋转、缩放四个基本过程；通过分析视觉伺服过程中图像特征变化规律，采用扩展图像特征补充传统图像特征的含义，以图像重心坐标、直线相对长度、两点距离、方向角等作为扩展图像特征与相机各自由度运动对应，通过图像特征误差直接控制机器人运动，实现不依赖图像雅可比矩阵的、解耦的视觉伺服。在CoppeliaSim平台进行对比仿真实验，结果表明本研究所提的方法与传统有标定视觉伺服在目标图像位置误差、相机位置误差和姿态误差相比分别降低了88%、94%和93%，并利用实物实验验证了本算法的有效性。

关键词: 机器人, 无标定视觉伺服, 扩展图像特征, 特征选择, 运动解耦

Abstract:

Aiming at the traditional uncalibrated visual servo relying on the estimation of image Jacobi matrix and the coupling of the motion of each degree of freedom of the camera, on the basis of image-based uncalibrated visual servo, an extended image features based uncalibrated visual servo method is proposed. By analyzing the relationship between image features and camera frames change in the visual servoing process, the visual servoing process in the image space is decomposed into four basic processes: translation, stretching, rotation and scaling; by analyzing the changing of image features in the visual servoing process, extended image features are used to complement the meaning of traditional image features, image center coordinates, relative length of a straight line, distance between two points, and direction angle are selected to correspond to the motion of each degree of freedom of the camera, and the robot's motion is directly controlled by the error of the image features, which realizes a completely decoupled visual servo that does not depend on the image Jacobian matrix. Comparative simulation experiments on CoppeliaSim platform show that compared with the traditional calibrated visual servoing, the method proposed in this study reduces the image position error, the camera position error, and orientation error by 88%, 94%, and 93% of respectively. The effectiveness of the algorithm is verified using physical experiments.

Key words: robot, uncalibrated visual servoing, extended image feature, feature selection, motion decoupling

中图分类号:

TP242.6

张淑珍,成煜坤,刘杨波等 . 基于扩展图像特征的无标定视觉伺服方法[J]. 系统仿真学报, 2025, 37(5): 1210-1221.

Zhang Shuzhen,Cheng Yukun,Liu Yangbo,et al . An Extended Image Features Based Uncalibrated Visual Servoing Method[J]. Journal of System Simulation, 2025, 37(5): 1210-1221.

图/表 14

图1

图2

图3

图4

图5

图6

图7

表1

5个视觉伺服任务定义

任务	初始位姿	期望位姿
1	(0, 0, 0, 0, 0, -1/6 $π$ )	(0, 0, 0, 0, 0, 0 )
2	(0, 0, -1.5, 0, 0, -2/9 $π$ )
3	(-0.08, -0.06, -0.2, 0, 0, -1/6 $π$ )
4	(-0.03, -0.1, -0.2, -1/36 $π$ , -1/9 $π$ , -1/6 $π$ )
5	(-0.2, 0.03, -0.2, 1/24 $π$ , 3/20 $π$ , -1/6 $π$ )

表1

表2

图8

图9

图10

图11

图12

参考文献 15

1	Chaumette Francois, Hutchinson Seth. Visual Servo Control. I. Basic Approaches[J]. IEEE Robotics & Automation Magazine, 2006, 13(4): 82-90.
2	陶波, 龚泽宇, 丁汉. 机器人无标定视觉伺服控制研究进展[J]. 力学学报, 2016, 48(4): 767-783.
	Tao Bo, Gong Zeyu, Ding Han. Survey on Uncalibrated Robot Visual Servoing Control[J]. Chinese Journal of Theoretical and Applied Mechanics, 2016, 48(4): 767-783.
3	Piepmeier J A, McMurray G V, Lipkin H. Uncalibrated Dynamic Visual Servoing[J]. IEEE Transactions on Robotics and Automation, 2004, 20(1): 143-147.
4	Liu Yunhui, Wang Hesheng, Wang Chengyou, et al. Uncalibrated Visual Servoing of Robots Using a Depth-independent Interaction Matrix[J]. IEEE Transactions on Robotics, 2006, 22(4): 804-817.
5	Chaumette François. Potential Problems of Unstability and Divergence in Image-based and Position-based Visual Servoing[C]//1999 European Control Conference (ECC). Piscataway: IEEE, 1999: 4549-4554.
6	马树军, 金铁铮, 王英蕾, 等. 一种无标定视觉伺服系统的快速跟踪策略[J]. 东北大学学报(自然科学版), 2020, 41(3): 355-360.
	Ma Shujun, Jin Tiezheng, Wang Yinglei, et al. A Fast Tracking Strategy for Uncalibrated Visual Servo System[J]. Journal of Northeastern University(Natural Science), 2020, 41(3): 355-360.
7	贾庆轩, 段嘉琪, 陈钢. 机器人在轨装配无标定视觉伺服对准方法[J]. 航空学报, 2021, 42(6): 617-626.
	Jia Qingxuan, Duan Jiaqi, Chen Gang. Uncalibrated Visual Servo of Space Robots Performing on-orbit Assembly Alignment Task[J]. Acta Aeronautica et Astronautica Sinica, 2021, 42(6): 617-626.
8	Li Tao, Yu Jinpeng, Qiu Quan, et al. Hybrid Uncalibrated Visual Servoing Control of Harvesting Robots with RGB-D Cameras[J]. IEEE Transactions on Industrial Electronics, 2023, 70(3): 2729-2738.
9	梁喜凤, 彭明, 路杰, 等. 基于自适应无迹卡尔曼滤波的采摘机械手视觉伺服控制方法[J]. 农业工程学报, 2019, 35(19): 230-237.
	Liang Xifeng, Peng Ming, Lu Jie, et al. Servo Control Method of Picking Manipulator Based on Adaptive Traceless Kalman Filter[J]. Transactions of the Chinese Society of Agricultural Engineering, 2019, 35(19): 230-237.
10	Gong Zeyu, Tao Bo, Yang Hua, et al. An Uncalibrated Visual Servo Method Based on Projective Homography[J]. IEEE Transactions on Automation Science and Engineering, 2018, 15(2): 806-817.
11	叶国强, 李伟光, 万好. 结合学习特征的图像矩视觉伺服方法[J]. 华南理工大学学报(自然科学版), 2017, 45(2): 99-107.
	Ye Guoqiang, Li Weiguang, Wan Hao. Image Moment-based Visual Servoing Method with Learning Features[J]. Journal of South China University of Technology(Natural Science Edition), 2017, 45(2): 99-107.
12	Zubair Arif, Fu Yili, Sohail Amjad, et al. Markerless Visual Servoing Using Virtual Face Tag and Image Moment Invariants[C]//2022 4th International Conference on Robotics and Computer Vision (ICRCV). Piscataway: IEEE, 2022: 123-128.
13	Cong V D. Visual Servoing Control of 4-DOF Palletizing Robotic Arm for Vision Based Sorting Robot System[J]. International Journal on Interactive Design and Manufacturing (IJIDeM), 2023, 17(2): 717-728.
14	Cong V D, Hanh L D. A New Decoupled Control Law for Image-based Visual Servoing Control of Robot Manipulators[J]. International Journal of Intelligent Robotics and Applications, 2022, 6(3): 576-585.
15	Wu Dongjie, Zhong Xungao, Zhang Xiaoli, et al. Uncalibrated Image-based Visual Servoing Based on Joint Space and Image moment[C]//2018 37th Chinese Control Conference (CCC). Piscataway: IEEE, 2018: 5391-5397.

算法	误差类型	任务1	任务2	任务3	任务4	任务5
IBVS	图像误差/像素	0.000 7	0.004 1	0.003 7	0.007 8	0.009 2
	相机位置误差/mm	0.307 7	1.434 1	1.077 8	3.762 0	4.917 0
	相机姿态误差/(°)	0.002 9	0.013 6	0.007 0	0.029 9	0.042 2
	轨迹长度/mm	5.152 9	152.716 7	238.004 7	267.610 8	322.033 7
E_IBUVS	图像误差/像素	0.000 0	0.000 0	0.000 0	0.000 0	0.001 1
	相机位置误差/mm	0.094 7	0.072 6	0.093 4	0.078 4	0.056 1
	相机姿态误差/(°)	0.000 7	0.000 4	0.000 9	0.000 8	0.002 8
	轨迹长度/mm	1.739 4	151.400 4	240.297 5	240.477 0	306.464 1

[1]	周晓晖, 李研强, 王勇, 赵德财, 杨逍瑶. 基于双启发式信息蚁群算法的机器人路径规划[J]. 系统仿真学报, 2025, 37(5): 1280-1289.
[2]	喻蝶, 鲍柏仲, 司言, 段暕, 詹小斌, 史铁林. 基于搜索步优化A*算法的移动机器人路径规划[J]. 系统仿真学报, 2025, 37(4): 1041-1050.
[3]	李敏, 张森, 曾祥光, 王刚, 张童伟, 谢地杰, 任文哲, 张滔. 基于深度强化学习的四足机器人单腿越障轨迹规划[J]. 系统仿真学报, 2025, 37(4): 895-909.
[4]	贺志刚, 李大焱, 王妮娅, 毛剑琳, 王宁. 一种含链式工作方式的多机器人协作路径规划算法[J]. 系统仿真学报, 2025, 37(4): 953-967.
[5]	林桂娟, 李子涵, 王宇. 基于全局关键点提取的改进A*算法全局路径规划研究[J]. 系统仿真学报, 2025, 37(3): 667-678.
[6]	房国强, 常海涛, 刘星, 刘正雄, 黄攀峰. 面向空间机器人辅助操作的任务规划方法研究[J]. 系统仿真学报, 2025, 37(2): 325-334.
[7]	李炯逸, 李强, 张新闻, Htet Zin Myo, 蔡永斌. 移动机器人用改进的双向A*二次路径规划算法[J]. 系统仿真学报, 2025, 37(2): 498-507.
[8]	张道勋, 陈谢沅澧, 钟铮语, 徐明, 郑志强, 卢惠民. 四足机器人稳定高效行进的多步态运动策略[J]. 系统仿真学报, 2025, 37(1): 13-24.
[9]	许建民, 宋雷, 邓冬冬, 陈尧箬, 杨炜. 基于多尺度A*与优化DWA算法融合的移动机器人路径规划[J]. 系统仿真学报, 2025, 37(1): 257-270.
[10]	姚万业, 庞泽伟, 孙沛杰, 王祝. 基于窗口化匹配估计的ORB-SLAM算法研究[J]. 系统仿真学报, 2024, 36(9): 2032-2042.
[11]	苑朝, 张耀, 赵亚冬, 徐大伟, 苑晶, 翟永杰. 基于全向轮的排管电缆巡检机器人建模及仿真[J]. 系统仿真学报, 2024, 36(9): 2100-2112.
[12]	徐健, 刘高峰, 赵一剑, 郑自立, 闫焕营. 装配机器人的数字孪生虚实同步及抓取方法[J]. 系统仿真学报, 2024, 36(9): 2181-2192.
[13]	孙海杰, 伞红军, 肖乐, 姚得鑫, 陈久朋, 杨晓园. 一种改进的移动机器人路径规划算法[J]. 系统仿真学报, 2024, 36(9): 2193-2207.
[14]	匡兴红, 黄傲威. 一种基于深度学习辅助的SINS/DVL组合导航方法[J]. 系统仿真学报, 2024, 36(8): 1810-1822.
[15]	康亮, 杜奕, 尹丽华. 一种面向异质多移动机器人的改进猫群算法[J]. 系统仿真学报, 2024, 36(8): 1958-1968.

基于扩展图像特征的无标定视觉伺服方法

An Extended Image Features Based Uncalibrated Visual Servoing Method

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 15

相关文章 15

编辑推荐

Metrics

本文评价