Hybrid position/force control of constrained robot manipulator based on a feedforward neural network

Lianfang Tian; Jun Wang; Zongyuan Mao

doi:10.1109/ICIT.2002.1189924

Hybrid position/force control of constrained robot manipulator based on a feedforward neural network

Lianfang Tian, Jun Wang, Zongyuan Mao

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

1 Citation (Scopus)

Abstract

In this paper, the control of the constrained robotic manipulators is addressed and the solution of a reduced order model is obtained through a nonlinear transformation. A set of differential-algebraic equations are first derived. Then controllers are designed for position and force control. The position control involves the position and velocity feedback of end-effector, while the force control is developed based on an artificial neural network. The weights of the neural network are updated on-line using the force error as the objective function. An example of a two DOF manipulator system is studied in detail. Comparison between conventional PID controller and the designed controller are made and a practical application is carried out. The results demonstrate remarkable performance of the system. © 2002 IEEE.

Original language	English
Title of host publication	IEEE ICIT’ 02 - 2002 IEEE International Conference on Industrial Technology
Subtitle of host publication	“Productivity Reincarnation through Robotics & Automation”
Publisher	IEEE
Pages	370-375
Volume	1
ISBN (Print)	0780376579
DOIs	https://doi.org/10.1109/ICIT.2002.1189924
Publication status	Published - Dec 2002
Externally published	Yes
Event	2002 IEEE International Conference on Industrial Technology (IEEE ICIT' 02): “Productivity Reincarnation through Robotics & Automation” - Shangri-La Hotel, Bangkok, Thailand Duration: 11 Dec 2002 → 14 Dec 2002

Conference

Conference	2002 IEEE International Conference on Industrial Technology (IEEE ICIT' 02)
Place	Thailand
City	Bangkok
Period	11/12/02 → 14/12/02

Access Output

10.1109/ICIT.2002.1189924

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{099cde7ec92a408ea2048af447a97dab,

title = "Hybrid position/force control of constrained robot manipulator based on a feedforward neural network",

abstract = "In this paper, the control of the constrained robotic manipulators is addressed and the solution of a reduced order model is obtained through a nonlinear transformation. A set of differential-algebraic equations are first derived. Then controllers are designed for position and force control. The position control involves the position and velocity feedback of end-effector, while the force control is developed based on an artificial neural network. The weights of the neural network are updated on-line using the force error as the objective function. An example of a two DOF manipulator system is studied in detail. Comparison between conventional PID controller and the designed controller are made and a practical application is carried out. The results demonstrate remarkable performance of the system. {\textcopyright} 2002 IEEE.",

author = "Lianfang Tian and Jun Wang and Zongyuan Mao",

year = "2002",

month = dec,

doi = "10.1109/ICIT.2002.1189924",

language = "English",

isbn = "0780376579",

volume = "1",

pages = "370--375",

booktitle = "IEEE ICIT{\textquoteright} 02 - 2002 IEEE International Conference on Industrial Technology",

publisher = "IEEE",

address = "United States",

note = "2002 IEEE International Conference on Industrial Technology (IEEE ICIT' 02) : “Productivity Reincarnation through Robotics & Automation” ; Conference date: 11-12-2002 Through 14-12-2002",

}

Tian, L, Wang, J & Mao, Z 2002, Hybrid position/force control of constrained robot manipulator based on a feedforward neural network. in IEEE ICIT’ 02 - 2002 IEEE International Conference on Industrial Technology: “Productivity Reincarnation through Robotics & Automation”. vol. 1, IEEE, pp. 370-375, 2002 IEEE International Conference on Industrial Technology (IEEE ICIT' 02), Bangkok, Thailand, 11/12/02. https://doi.org/10.1109/ICIT.2002.1189924

Hybrid position/force control of constrained robot manipulator based on a feedforward neural network. / Tian, Lianfang; Wang, Jun; Mao, Zongyuan.
IEEE ICIT’ 02 - 2002 IEEE International Conference on Industrial Technology: “Productivity Reincarnation through Robotics & Automation”. Vol. 1 IEEE, 2002. p. 370-375.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Hybrid position/force control of constrained robot manipulator based on a feedforward neural network

AU - Tian, Lianfang

AU - Wang, Jun

AU - Mao, Zongyuan

PY - 2002/12

Y1 - 2002/12

N2 - In this paper, the control of the constrained robotic manipulators is addressed and the solution of a reduced order model is obtained through a nonlinear transformation. A set of differential-algebraic equations are first derived. Then controllers are designed for position and force control. The position control involves the position and velocity feedback of end-effector, while the force control is developed based on an artificial neural network. The weights of the neural network are updated on-line using the force error as the objective function. An example of a two DOF manipulator system is studied in detail. Comparison between conventional PID controller and the designed controller are made and a practical application is carried out. The results demonstrate remarkable performance of the system. © 2002 IEEE.

AB - In this paper, the control of the constrained robotic manipulators is addressed and the solution of a reduced order model is obtained through a nonlinear transformation. A set of differential-algebraic equations are first derived. Then controllers are designed for position and force control. The position control involves the position and velocity feedback of end-effector, while the force control is developed based on an artificial neural network. The weights of the neural network are updated on-line using the force error as the objective function. An example of a two DOF manipulator system is studied in detail. Comparison between conventional PID controller and the designed controller are made and a practical application is carried out. The results demonstrate remarkable performance of the system. © 2002 IEEE.

UR - http://www.scopus.com/inward/record.url?scp=70249096461&partnerID=8YFLogxK

UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-70249096461&origin=recordpage

U2 - 10.1109/ICIT.2002.1189924

DO - 10.1109/ICIT.2002.1189924

M3 - RGC 32 - Refereed conference paper (with host publication)

SN - 0780376579

VL - 1

SP - 370

EP - 375

BT - IEEE ICIT’ 02 - 2002 IEEE International Conference on Industrial Technology

PB - IEEE

T2 - 2002 IEEE International Conference on Industrial Technology (IEEE ICIT' 02)

Y2 - 11 December 2002 through 14 December 2002

ER -

Hybrid position/force control of constrained robot manipulator based on a feedforward neural network

Abstract

Conference

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this