|Table of Contents|

Dynamic grasping parameter estimation based on feedforward radial basis function network(PDF)

Journal of Shenzhen University Science and Engineering[ISSN:1000-2618/CN:44-1401/N]

Issue:
2022 Vol.39 No.3(237-362)
Page:
334-342
Research Field:
Electronics and Information Science

Info

Title:
Dynamic grasping parameter estimation based on feedforward radial basis function network
Author(s):
WANG Jianqiang1 HUANG Kaiqi1 and SU Jianhua2
1) School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, Jiangxi Province, P. R. China
2) The State Key Laboratory for Management and Control of Complex System, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, P. R. China
Keywords:
robot technology motion estimation kernel correlation filter Kalman filter feed-forward radial basis function dynamic crawling
PACS:
TP242;TP181
DOI:
10.3724/SP.J.1249.2022.03334
Abstract:
In this paper, we propose a motion estimation method based on a feed-forward radial basis network for grasping arbitrary moving objects. We first employ a kernel correlation filtering (KCF) algorithm to track the target position in real-time and establish the motion model of the target. Using the feed-forward radial base network, we then adjust the sampling time of the Kalman filter (KF) to predict the motion parameters of the target. Since that, we can reduce the computing time and improve the accuracy of the estimation of the motion parameters. Compared with the feed-forward perceptron network, the proposed method shortens the required time for grasping by 20%, which can avoid a failure grasp due to the arbitrary movement of the object in grasping.

References:

[1] ROSS D A, LIM J, LIN R, et al. Incremental learning for robust visual tracking [J]. International Journal of Computer Vision, 2008,77(1): 125-141.
[2] GALOOGAHI H K, FAGG A, LUCEY S. Learning background-aware correlation filters for visual tracking [C]// IEEE International Conference on Computer Vision. Venice, Italy: IEEE, 2017: 1144-1152.
[3] ZDENEK K, KRYSTIAN M, JIRI M. Tracking learning detection [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2012, 34(7): 1409-1422.
[4] HENRIQUES J F, CASEIRO R, MARTINS P, et al. High-speed tracking with kernelized correlation filters [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37(3): 583-596.
[5] VERMA S, NEHA Y. Past, present, and future of electronic word of mouth (EWOM) [J]. Journal of Interactive Marketing, 2021, 53: 111-128.
[6] ZHOU Hailing, KONG Hui, WEI Lei, et al. Efficient road detection and tracking for unmanned aerial vehicle [J]. IEEE Transactions on Intelligent Transportation Systems, 2015, 16(1): 297-309.
[7] 崔吉,张燕超.基于卡尔曼滤波的多运动目标跟踪算法研究[J].影像技术,2010,22(3):11-15.
CUI Ji, ZHANG Yanchao. Research on multi-moving target tracking algorithm based on Kalman filter [J]. Image Technology, 2010, 22(3): 11-15.(in Chinese)
[8] 邓桦.机械臂空间目标视觉抓取的研究[D].哈尔滨:哈尔滨工业大学,2013.
DENG Ye. Research on space object vision capture of manipulator [D]. Harbin: College of mechanical and electrical engineering, 2013.(in Chinese)
[9] JULIER S J, UHLMANN J K. New extension of the Kalman filter to nonlinear systems [C]// Proceedings of Signal Processing, Sensor Fusion, and Target Recognition. Orlando, USA: SPIE, 1997, 3068: 182-193.
[10] JULIER S J, UHLMANN J K, DURRANT-WHYTE H F. A new approach for filtering nonlinear systems [C]// Proceedings of 1995 American Control Conference. Seattle, USA: IEEE, 1995, 3: 1628-1632.
[11] 周卫东,乔相伟,任蕾,等.QUKF算法及其在SINS初始对准中的应用[J].仪器仪表学报,2010,31(2):264-269.
ZHOU Weidong, QIAO Xiangwei, REN Lei, et al. Quaternion unsecnted Kalman filter and its application to initial alignment of SINS [J]. Chinese Journal of Scientific Instrument, 2010, 31(2): 264-269.(in Chinese)
[12] CHOUKROUN D, BAR-ITZHACK I Y, OSHMAN Y. Novel quaternion Kalman filter [J]. IEEE Transactions on Aerospace and Electronic Systems, 2006, 42(1): 174-190.
[13] HUANG Haoqian, SHI Rengdu, ZHOU Jun, et al. Attitude determination method integrating square-root cubature Kalman filter with expectation-maximization for inertial navigation system applied to underwater glider [J]. Review of Scientific Instruments, 2019, 90(9): 095001.
[14] CHOUKROUN D, BAR-ITZHACK I Y, OSHMAN Y. Novel quaternion Kalman filter [J]. IEEE Transactions on Aerospace and Electronic Systems, 2006, 42(1): 174-190.
[15] 安旭文.基于单目视觉的目标识别与跟踪系统研究[D].武汉:华中科技大学,2014.
AN Xuwen. Research on target recognition and tracking system based on monocular vision [D]. Wuhan: Huazhong University of Science and Technology, 2014.(in Chinese)
[16] 林雪原,鞠建波.利用神经网络预测的GPS/SINS组合导航系统算法研究[J].武汉大学学报:信息科学版,2011,36(5):602-604.
LIN Xueyuan, JU Jianbo. GPS/SINS integrated navigation algorithm based on neural network prediction [J]. Geomatics and Information Science of Wuhan University, 2011, 36(5): 602-604.(in Chinese)
[17] 夏志伟.移动机械臂目标抓取轨迹规划与控制系统设计[D].哈尔滨:哈尔滨工程大学,2019.
XIA Zhiwei. Design of trajectory planning and control system for target grasping of mobile manipulator [D]. Harbin: Harbin Engineering University, 2019.(in Chinese)
[18] BUTTAZZO G C, ALLOTTA B, FANIZZA F P. Mousebuster: a robot system for catching fast moving objects by vision [C]// Proceedings IEEE International Conference on Robotics and Automation. Atlanta, USA: IEEE, 1993: 932-937.
[19] 李宇飞,高朝辉,申麟.基于视觉的机械臂空间目标抓取策略研究[J].中国科学:技术科学,2015,45(1):31-35.
LI Yufei, GAO Zhaohui, SHEN Lin. Study of vision-based space target capturing strategy for manipulators [J]. Scientia Sinica Technologica, 2015, 45(1): 31-35.(in Chinese)
[20] 郭迪.面向机器人操作的目标检测与抓取规划研究[D].北京:清华大学,2016.
GUO Di. Research on object detection and grasping planning for robot operation [D]. Beijing: Tsinghua University, 2016.(in Chinese)

Memo

Memo:
-