Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers

Standard

Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers. / Fang, Wubing; Chao, Fei; Lin, Chih Min; Zhou, Dajun; Yang, Longzhi; Chang, Xiang; Shen, Qiang; Shang, Changjing.

In: IEEE Transactions on Industrial Informatics, Vol. 17, No. 3, 9095225, 18.05.2020, p. 2282-2291.

Research output: Contribution to journalArticlepeer-review

Harvard

Fang, W, Chao, F, Lin, CM, Zhou, D, Yang, L, Chang, X, Shen, Q & Shang, C 2020, 'Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers', IEEE Transactions on Industrial Informatics, vol. 17, no. 3, 9095225, pp. 2282-2291. https://doi.org/10.1109/TII.2020.2995142

APA

Fang, W., Chao, F., Lin, C. M., Zhou, D., Yang, L., Chang, X., Shen, Q., & Shang, C. (2020). Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers. IEEE Transactions on Industrial Informatics, 17(3), 2282-2291. [9095225]. https://doi.org/10.1109/TII.2020.2995142

Vancouver

Fang W, Chao F, Lin CM, Zhou D, Yang L, Chang X et al. Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers. IEEE Transactions on Industrial Informatics. 2020 May 18;17(3):2282-2291. 9095225. https://doi.org/10.1109/TII.2020.2995142

Author

Fang, Wubing ; Chao, Fei ; Lin, Chih Min ; Zhou, Dajun ; Yang, Longzhi ; Chang, Xiang ; Shen, Qiang ; Shang, Changjing. / Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers. In: IEEE Transactions on Industrial Informatics. 2020 ; Vol. 17, No. 3. pp. 2282-2291.

Bibtex - Download

@article{eb4f5f6a471f4257bdd60386d5783579,
title = "Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers",
abstract = "It has been a challenging task for a robotic arm to accurately reach and grasp objects, which has drawn much research attention. This article proposes a robotic hand-eye coordination system by simulating the human behavior pattern to achieve a fast and robust reaching ability. This is achieved by two neural-network-based controllers, including a rough reaching movement controller implemented by a pretrained radial basis function for rough reaching movements, and a correction movement controller built from a specifically designed brain emotional nesting network (BENN) for smooth correction movements. In particular, the proposed BENN is designed with high nonlinear mapping ability, with its adaptive laws derived from the Lyapunov stability theorem; from this, the robust tracking performance and accordingly the stability of the proposed control system are guaranteed by the utilization of the $H^{\infty }$ control approach. The proposed BENN is validated and evaluated by a chaos synchronization simulation, and the overall control system by object grasping tasks through a physical robotic arm in a real-world environment. The experimental results demonstrate the superiority of the proposed control system in reference to those with single neural networks. ",
keywords = "Neural-network-based controller, robotic hand-eye coordination, robotic reaching movement",
author = "Wubing Fang and Fei Chao and Lin, {Chih Min} and Dajun Zhou and Longzhi Yang and Xiang Chang and Qiang Shen and Changjing Shang",
note = "Funding Information: Manuscript received January 30, 2020; revised April 15, 2020; accepted May 10, 2020. Date of publication May 18, 2020; date of current version November 20, 2020. This work was supported in part by the Fundamental Research Funds for the Central Universities under Grant 20720190142, in part by the National Natural Science Foundation of China under Grant 61673322, Grant 61673326, and Grant 91746103, and in part by the European Union{\textquoteright}s Horizon 2020 Research and Innovation Programme under the Marie Sklodowska-Curie under Grant 663830. Paper no. TII-20-0448. (Corresponding author: Fei Chao.) Wubing Fang is with the Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen 361005, China (e-mail: 18551626891@163.com). Publisher Copyright: {\textcopyright} 2005-2012 IEEE.",
year = "2020",
month = may,
day = "18",
doi = "10.1109/TII.2020.2995142",
language = "English",
volume = "17",
pages = "2282--2291",
journal = "IEEE Transactions on Industrial Informatics",
issn = "1551-3203",
publisher = "IEEE Press",
number = "3",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Visual-Guided Robotic Object Grasping Using Dual Neural Network Controllers

AU - Fang, Wubing

AU - Chao, Fei

AU - Lin, Chih Min

AU - Zhou, Dajun

AU - Yang, Longzhi

AU - Chang, Xiang

AU - Shen, Qiang

AU - Shang, Changjing

N1 - Funding Information: Manuscript received January 30, 2020; revised April 15, 2020; accepted May 10, 2020. Date of publication May 18, 2020; date of current version November 20, 2020. This work was supported in part by the Fundamental Research Funds for the Central Universities under Grant 20720190142, in part by the National Natural Science Foundation of China under Grant 61673322, Grant 61673326, and Grant 91746103, and in part by the European Union’s Horizon 2020 Research and Innovation Programme under the Marie Sklodowska-Curie under Grant 663830. Paper no. TII-20-0448. (Corresponding author: Fei Chao.) Wubing Fang is with the Department of Artificial Intelligence, School of Informatics, Xiamen University, Xiamen 361005, China (e-mail: 18551626891@163.com). Publisher Copyright: © 2005-2012 IEEE.

PY - 2020/5/18

Y1 - 2020/5/18

N2 - It has been a challenging task for a robotic arm to accurately reach and grasp objects, which has drawn much research attention. This article proposes a robotic hand-eye coordination system by simulating the human behavior pattern to achieve a fast and robust reaching ability. This is achieved by two neural-network-based controllers, including a rough reaching movement controller implemented by a pretrained radial basis function for rough reaching movements, and a correction movement controller built from a specifically designed brain emotional nesting network (BENN) for smooth correction movements. In particular, the proposed BENN is designed with high nonlinear mapping ability, with its adaptive laws derived from the Lyapunov stability theorem; from this, the robust tracking performance and accordingly the stability of the proposed control system are guaranteed by the utilization of the $H^{\infty }$ control approach. The proposed BENN is validated and evaluated by a chaos synchronization simulation, and the overall control system by object grasping tasks through a physical robotic arm in a real-world environment. The experimental results demonstrate the superiority of the proposed control system in reference to those with single neural networks.

AB - It has been a challenging task for a robotic arm to accurately reach and grasp objects, which has drawn much research attention. This article proposes a robotic hand-eye coordination system by simulating the human behavior pattern to achieve a fast and robust reaching ability. This is achieved by two neural-network-based controllers, including a rough reaching movement controller implemented by a pretrained radial basis function for rough reaching movements, and a correction movement controller built from a specifically designed brain emotional nesting network (BENN) for smooth correction movements. In particular, the proposed BENN is designed with high nonlinear mapping ability, with its adaptive laws derived from the Lyapunov stability theorem; from this, the robust tracking performance and accordingly the stability of the proposed control system are guaranteed by the utilization of the $H^{\infty }$ control approach. The proposed BENN is validated and evaluated by a chaos synchronization simulation, and the overall control system by object grasping tasks through a physical robotic arm in a real-world environment. The experimental results demonstrate the superiority of the proposed control system in reference to those with single neural networks.

KW - Neural-network-based controller

KW - robotic hand-eye coordination

KW - robotic reaching movement

UR - http://www.scopus.com/inward/record.url?scp=85097710486&partnerID=8YFLogxK

U2 - 10.1109/TII.2020.2995142

DO - 10.1109/TII.2020.2995142

M3 - Article

AN - SCOPUS:85097710486

VL - 17

SP - 2282

EP - 2291

JO - IEEE Transactions on Industrial Informatics

JF - IEEE Transactions on Industrial Informatics

SN - 1551-3203

IS - 3

M1 - 9095225

ER -

Show download statistics
View graph of relations
Citation formats