Uncalibrated visual servo control with neural network

873 Views
1017 Downloads
Export citation: ABNT
KLOBUČAR, Rok ;ČUŠ, Jure ;ŠAFARIČ, Riko ;BREZOČNIK, Miran .
Uncalibrated visual servo control with neural network. 
Strojniški vestnik - Journal of Mechanical Engineering, [S.l.], v. 54, n.9, p. 619-627, august 2017. 
ISSN 0039-2480.
Available at: <https://www.sv-jme.eu/article/uncalibrated-visual-servo-control-with-neural-network/>. Date accessed: 27 jan. 2021. 
doi:http://dx.doi.org/.
Klobučar, R., Čuš, J., Šafarič, R., & Brezočnik, M.
(2008).
Uncalibrated visual servo control with neural network.
Strojniški vestnik - Journal of Mechanical Engineering, 54(9), 619-627.
doi:http://dx.doi.org/
@article{.,
	author = {Rok  Klobučar and Jure  Čuš and Riko  Šafarič and Miran  Brezočnik},
	title = {Uncalibrated visual servo control with neural network},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {54},
	number = {9},
	year = {2008},
	keywords = {robots; neural networks; visual servoing; parallel manipulators; },
	abstract = {Research into robotics visual servo systems is an important content in the robotics field. This paper describes a control approach for a robotics manipulator. In this paper, a multilayer feedforward network is applied to a robot visual servo control problem. The model uses new neural network architecture and a new algorithm for modifying neural connection strength. No a-prior knowledge is required of robot kinematics and camera calibration. The network is trained using an end-effector position. After training, performance is measured by having the network generate joint-angles for arbitrary end effector trajectories. A 2-degrees-of-freedom (DOF) parallel manipulator was used for the study. It was discovered that neural networks provide a simple and effective way of controlling robotic tasks. This paper explores the application of a neural network for approximating nonlinear transformation relating to the robotćs tip-position, from the image coordinates to its joint coordinates. Real experimental examples are given to illustrate the significance of this method. Experimental results are compared with a similar method called the Broyden method, for uncalibrated visual servo-control.},
	issn = {0039-2480},	pages = {619-627},	doi = {},
	url = {https://www.sv-jme.eu/article/uncalibrated-visual-servo-control-with-neural-network/}
}
Klobučar, R.,Čuš, J.,Šafarič, R.,Brezočnik, M.
2008 August 54. Uncalibrated visual servo control with neural network. Strojniški vestnik - Journal of Mechanical Engineering. [Online] 54:9
%A Klobučar, Rok 
%A Čuš, Jure 
%A Šafarič, Riko 
%A Brezočnik, Miran 
%D 2008
%T Uncalibrated visual servo control with neural network
%B 2008
%9 robots; neural networks; visual servoing; parallel manipulators; 
%! Uncalibrated visual servo control with neural network
%K robots; neural networks; visual servoing; parallel manipulators; 
%X Research into robotics visual servo systems is an important content in the robotics field. This paper describes a control approach for a robotics manipulator. In this paper, a multilayer feedforward network is applied to a robot visual servo control problem. The model uses new neural network architecture and a new algorithm for modifying neural connection strength. No a-prior knowledge is required of robot kinematics and camera calibration. The network is trained using an end-effector position. After training, performance is measured by having the network generate joint-angles for arbitrary end effector trajectories. A 2-degrees-of-freedom (DOF) parallel manipulator was used for the study. It was discovered that neural networks provide a simple and effective way of controlling robotic tasks. This paper explores the application of a neural network for approximating nonlinear transformation relating to the robotćs tip-position, from the image coordinates to its joint coordinates. Real experimental examples are given to illustrate the significance of this method. Experimental results are compared with a similar method called the Broyden method, for uncalibrated visual servo-control.
%U https://www.sv-jme.eu/article/uncalibrated-visual-servo-control-with-neural-network/
%0 Journal Article
%R 
%& 619
%P 9
%J Strojniški vestnik - Journal of Mechanical Engineering
%V 54
%N 9
%@ 0039-2480
%8 2017-08-21
%7 2017-08-21
Klobučar, Rok, Jure  Čuš, Riko  Šafarič, & Miran  Brezočnik.
"Uncalibrated visual servo control with neural network." Strojniški vestnik - Journal of Mechanical Engineering [Online], 54.9 (2008): 619-627. Web.  27 Jan. 2021
TY  - JOUR
AU  - Klobučar, Rok 
AU  - Čuš, Jure 
AU  - Šafarič, Riko 
AU  - Brezočnik, Miran 
PY  - 2008
TI  - Uncalibrated visual servo control with neural network
JF  - Strojniški vestnik - Journal of Mechanical Engineering
DO  - 
KW  - robots; neural networks; visual servoing; parallel manipulators; 
N2  - Research into robotics visual servo systems is an important content in the robotics field. This paper describes a control approach for a robotics manipulator. In this paper, a multilayer feedforward network is applied to a robot visual servo control problem. The model uses new neural network architecture and a new algorithm for modifying neural connection strength. No a-prior knowledge is required of robot kinematics and camera calibration. The network is trained using an end-effector position. After training, performance is measured by having the network generate joint-angles for arbitrary end effector trajectories. A 2-degrees-of-freedom (DOF) parallel manipulator was used for the study. It was discovered that neural networks provide a simple and effective way of controlling robotic tasks. This paper explores the application of a neural network for approximating nonlinear transformation relating to the robotćs tip-position, from the image coordinates to its joint coordinates. Real experimental examples are given to illustrate the significance of this method. Experimental results are compared with a similar method called the Broyden method, for uncalibrated visual servo-control.
UR  - https://www.sv-jme.eu/article/uncalibrated-visual-servo-control-with-neural-network/
@article{{}{.},
	author = {Klobučar, R., Čuš, J., Šafarič, R., Brezočnik, M.},
	title = {Uncalibrated visual servo control with neural network},
	journal = {Strojniški vestnik - Journal of Mechanical Engineering},
	volume = {54},
	number = {9},
	year = {2008},
	doi = {},
	url = {https://www.sv-jme.eu/article/uncalibrated-visual-servo-control-with-neural-network/}
}
TY  - JOUR
AU  - Klobučar, Rok 
AU  - Čuš, Jure 
AU  - Šafarič, Riko 
AU  - Brezočnik, Miran 
PY  - 2017/08/21
TI  - Uncalibrated visual servo control with neural network
JF  - Strojniški vestnik - Journal of Mechanical Engineering; Vol 54, No 9 (2008): Strojniški vestnik - Journal of Mechanical Engineering
DO  - 
KW  - robots, neural networks, visual servoing, parallel manipulators, 
N2  - Research into robotics visual servo systems is an important content in the robotics field. This paper describes a control approach for a robotics manipulator. In this paper, a multilayer feedforward network is applied to a robot visual servo control problem. The model uses new neural network architecture and a new algorithm for modifying neural connection strength. No a-prior knowledge is required of robot kinematics and camera calibration. The network is trained using an end-effector position. After training, performance is measured by having the network generate joint-angles for arbitrary end effector trajectories. A 2-degrees-of-freedom (DOF) parallel manipulator was used for the study. It was discovered that neural networks provide a simple and effective way of controlling robotic tasks. This paper explores the application of a neural network for approximating nonlinear transformation relating to the robotćs tip-position, from the image coordinates to its joint coordinates. Real experimental examples are given to illustrate the significance of this method. Experimental results are compared with a similar method called the Broyden method, for uncalibrated visual servo-control.
UR  - https://www.sv-jme.eu/article/uncalibrated-visual-servo-control-with-neural-network/
Klobučar, Rok, Čuš, Jure, Šafarič, Riko, AND Brezočnik, Miran.
"Uncalibrated visual servo control with neural network" Strojniški vestnik - Journal of Mechanical Engineering [Online], Volume 54 Number 9 (21 August 2017)

Authors

Affiliations

  • University of Maribor, Faculty of Electrical Engineering and Computer Science, Slovenia
  • University of Maribor, Faculty of Electrical Engineering and Computer Science, Slovenia
  • University of Maribor, Faculty of Electrical Engineering and Computer Science, Slovenia
  • University of Maribor, Faculty of Mechanical Engineering, Slovenia

Paper's information

Strojniški vestnik - Journal of Mechanical Engineering 54(2008)9, 619-627

Research into robotics visual servo systems is an important content in the robotics field. This paper describes a control approach for a robotics manipulator. In this paper, a multilayer feedforward network is applied to a robot visual servo control problem. The model uses new neural network architecture and a new algorithm for modifying neural connection strength. No a-prior knowledge is required of robot kinematics and camera calibration. The network is trained using an end-effector position. After training, performance is measured by having the network generate joint-angles for arbitrary end effector trajectories. A 2-degrees-of-freedom (DOF) parallel manipulator was used for the study. It was discovered that neural networks provide a simple and effective way of controlling robotic tasks. This paper explores the application of a neural network for approximating nonlinear transformation relating to the robotćs tip-position, from the image coordinates to its joint coordinates. Real experimental examples are given to illustrate the significance of this method. Experimental results are compared with a similar method called the Broyden method, for uncalibrated visual servo-control.

robots; neural networks; visual servoing; parallel manipulators;