[1]XIE Mingyang,WU Wei,XU Chengyong,et al.Visual servoing-based adaptive impedance control technology for collaborative robots[J].CAAI Transactions on Intelligent Systems,2025,20(6):1474-1482.[doi:10.11992/tis.202504008]
Copy
Visual servoing-based adaptive impedance control technology for collaborative robots
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
20
Number of periods:
2025 6
Page number:
1474-1482
Column:
学术论文—机器人
Public date:
2025-11-05
- Title:
- Visual servoing-based adaptive impedance control technology for collaborative robots
- Keywords:
- collaborative robot; robot grasping; target detection; compliant manipulation; deep learning; impedance control; optimization of capture posture; visual servo
- CLC:
- TP241
- DOI:
- 10.11992/tis.202504008
- Abstract:
- When operated in human–robot coexistent unstructured environments, collaborative robots face various challenges, such as low target recognition accuracy, suboptimal grasping poses, and difficulties in achieving compliant manipulation under dynamic unknown scenarios. To address these issues, this study proposed a vision servoing–based adaptive impedance control technique. The proposed method enabled compliant grasping of objects with varying stiffness characteristics and geometric configurations by the robot. First, an improved target detection algorithm based on the ResNet (residual network) was developed to generate an optimal capture prediction frame by inputting the RGBD (red-green-blue-depth) image of the captured target. Second, an adaptive impedance control strategy was proposed for the robot end effector, and the impedance parameters were adaptively adjusted using fuzzy control. Finally, a fuzzy adaptive impedance control system based on visual servoing was constructed, and experiments on object recognition and compliant grasping were conducted. Results showed that the proposed method enhanced the generalization capability and success rate of target recognition in grasping tasks and considerably improved manipulation compliance. Compared with existing adaptive impedance control strategies, the proposed method achieved 66.3% and 45.9% improvements in compliant metrics.
- References:
-
[1] 张霖, 谢开鑫, 郑显华, 等. 多机器人系统感知能力和控制体系结构综述[J]. 智能系统学报, 2024, 19(4): 767-790.
ZHANG Lin, XIE Kaixin, ZHENG Xianhua, et al. A survey on perception ability and control architecture of multi-robot system[J]. CAAI transactions on intelligent systems, 2024, 19(4): 767-790.
[2] 季肖枫, 顾娜, 陆佳皓, 等. 船舶吊运机械臂焊接接头超声无损智能检测研究[J]. 舰船科学技术, 2024, 46(24): 149-154.
JI Xiaofeng, GU Na, LU Jiahao, et al. Ltrasonic non destructive intelligent testing of welding joints in ship crane arm[J]. Ship science and technology, 2024, 46(24): 149-154.
[3] SAHU M, ISHIDA H, CONNOLLY L, et al. ENTRI: enhanced navigational toolkit for robotic interventions[J]. IEEE transactions on medical robotics and bionics, 2024, 6(4): 1405-1408.
[4] 黎小巨, 陈洵凛, 祝华春. 深度学习引导的喷涂产线工件自动识别及分拣[J]. 机床与液压, 2025, 53(8): 93-100.
LI Xiaoju, CHEN Xunlin, ZHU Huachun. Workpieces automatic recognition and sorting of spray painting production line guided by deep learning[J]. Machine tool & hydraulics, 2025, 53(8): 93-100.
[5] 李娜, 高笑, 杨磊, 等. 基于改进算法融合与切换的采摘机械臂路径动态规划[J]. 农业机械学报, 2024, 55(11): 221-230,272.
LI Na, GAO Xiao, YANG Lei, et al. Dynamic path planning for picking robot arm based on improved algorithm fusion and switching[J]. Transactions of the Chinese society for agricultural machinery, 2024, 55(11): 221-230,272.
[6] 李秀智, 李家豪, 张祥银, 等. 基于深度学习的机器人最优抓取姿态检测方法[J]. 仪器仪表学报, 2020, 41(5): 108-117.
LI Xiuzhi, LI Jiahao, ZHANG Xiangyin, et al. Detection method of robot optimal grasp posture based on deep learning[J]. Chinese journal of scientific instrument, 2020, 41(5): 108-117.
[7] 郭勇, 赖广. 工业机器人关节空间轨迹规划及优化研究综述[J]. 机械传动, 2020, 44(2): 154-165.
GUO Yong, LAI Guang. Review of joint space trajectory planning and optimization for industrial robot[J]. Journal of mechanical transmission, 2020, 44(2): 154-165.
[8] WU Wei, XIE Mingyang, ZHANG Min, et al. Nonlinear model predictive control for industrial robot arms based on feedforward compensation[C]//2024 43rd Chinese Control Conference. Kunming: IEEE, 2024: 2945-2952.
[9] ULAGAOOZHIAN C, DUCHAINE V. A novel human-safe robotic gripper: an application of a programmable permanent magnet actuator[C]//2022 IEEE/RSJ International Conference on Intelligent Robots and Systems. Kyoto: IEEE, 2022: 4646-4652.
[10] KONG Xiaohong, LI Xinjian, ZHU Xinxin, et al. Detection model based on improved faster-RCNN in apple orchard environment[J]. Intelligent systems with applications, 2024, 21: 200325.
[11] HUSSAIN M. YOLOv1 to v8: unveiling each variant–a comprehensive review of YOLO[J]. IEEE access, 2024, 12: 42816-42833.
[12] LENZ I, LEE H, SAXENA A. Deep learning for detecting robotic grasps[J]. The international journal of robotics research, 2015, 34(4/5): 705-724.
[13] KUMRA S, KANAN C. Robotic grasp detection using deep convolutional neural networks[C]//2017 IEEE/RSJ International Conference on Intelligent Robots and Systems. Vancouver: IEEE, 2017: 769-776.
[14] 刘万军, 姜岚, 曲海成, 等. 融合CNN与Transformer的MRI脑肿瘤图像分割[J]. 智能系统学报, 2024, 19(4): 1007-1015.
LIU Wanjun, JIANG Lan, QU Haicheng, et al. MRI brain tumor image segmentation by fusing CNN and Transformer[J]. CAAI transactions on intelligent systems, 2024, 19(4): 1007-1015.
[15] MORRISON D, CORKE P, LEITNER J. Learning robust, real-time, reactive robotic grasping[J]. The international journal of robotics research, 2020, 39(2/3): 183-201.
[16] HOGAN N. Impedance control: an approach to manipulation[C]//1984 American Control Conference. San Diego: IEEE, 1984: 304-313.
[17] BYUN J, KIM J, EOM D, et al. Image-based time-varying contact force control of aerial manipulator using robust impedance filter[J]. IEEE robotics and automation letters, 2024, 9(5): 4854-4861.
[18] XIU Bingkai, LI Zhan, PANG Bo, et al. Intelligent force tracking impedance control for aerial manipulator via characteristic model[J]. Nonlinear dynamics, 2025: 1-15.
[19] ZHANG Jianjun, LI Han, LIU Qunpo, et al. The model reference adaptive impedance control for underwater manipulator compliant operation[J]. Transactions of the institute of measurement and control, 2023, 45(11): 2135-2148.
[20] WU Changqu, WANG Zhuang, ZHANG Yuqiu, et al. Dexterous hand-object interaction control based on adaptive impedance algorithm[M]//Intelligent Robotics and Applications. Singapore: Springer Nature Singapore, 2023: 3-14.
[21] NAZMARA G R, NETO P, AGUIAR A P. Robust learning-based impedance control of robotic manipulators[C]//CONTROLO 2024: Proceedings of the 16th APCA International Conference on Automatic Control and Soft Computing. Porto: Springer Nature, 2025, 1325: 297.
[22] ZHU Xiang, KANG Shucheng, CHEN Jianyu. A contact-safe reinforcement learning framework for contact-rich robot manipulation[C]//2022 IEEE/RSJ International Conference on Intelligent Robots and Systems. Kyoto: IEEE, 2022: 2476-2482.
[23] MEI Zhimin, LI Yifan, ZHU Rongbo, et al. Intelligent fruit localization and grasping method based on YOLO VX model and 3D vision[J]. Agriculture, 2025, 15(14): 1508.
[24] HUI Nanmu, WU Xiaohui, HAN Xiaowei, et al. A robotic arm visual grasp detection algorithm combining 2D images and 3D point clouds[J]. Applied mechanics and materials, 2024, 919: 209-223.
[25] SONG Yanan, GAO Liang, LI Xinyu, et al. A novel robotic grasp detection method based on region proposal networks[J]. Robotics and computer-integrated manufacturing, 2020, 65: 101963.
[26] JHANG J Y, LIN Chengjian. Optimizing parameters of YOLO model through uniform experimental design for gripping tasks performed by an Internet of Things-based robotic arm[J]. Internet of Things, 2024, 27: 101332.
[27] STENO P, ALSADOON A, PRASAD P W C, et al. A novel enhanced region proposal network and modified loss function: threat object detection in secure screening using deep learning[J]. The journal of supercomputing, 2021, 77(4): 3840-3869.
- Similar References:
Memo
-
Last Update:
1900-01-01