Ghent University Academic Bibliography

Advanced

Towards learning inverse kinematics with a neural network based tracking controller

Tim Waegeman UGent and Benjamin Schrauwen UGent (2011) Lecture Notes in Computer Science. 7064(3). p.441-448
abstract
Learning an inverse kinematic model of a robot is a well studied subject. However, achieving this without information about the geometric characteristics of the robot is less investigated. In this work, a novel control approach is presented based on a recurrent neural network. Without any prior knowledge about the robot, this control strategy learns to control the iCub’s robot arm online by solving the inverse kinematic problem in its control region. Because of its exploration strategy the robot starts to learn by generating and observing random motor behavior. The modulation and generalization capabilities of this approach are investigated as well.
Please use this url to cite or link to this publication:
author
organization
year
type
conference
publication status
published
subject
keyword
Adaptive control, Feedback control, Inverse kinematics, Neural network (NN), Reservoir computing (RC)
in
Lecture Notes in Computer Science
Lect. Notes Comput. Sci.
editor
Bao-Liang Lu, Liqing Zhang and James Kwok
volume
7064
issue
3
issue title
Neural information processing
pages
441 - 448
publisher
Springer
place of publication
Berlin, Germany
conference name
18th International Conference on Neural Information Processing (ICONIP 2011)
conference location
Shanghai, PR China
conference start
2011-11-13
conference end
2011-11-17
Web of Science type
Proceedings Paper
Web of Science id
000307328500050
ISSN
0302-9743
ISBN
9783642249648
DOI
10.1007/978-3-642-24965-5_50
language
English
UGent publication?
yes
classification
P1
copyright statement
I have transferred the copyright for this publication to the publisher
id
1948358
handle
http://hdl.handle.net/1854/LU-1948358
date created
2011-11-24 09:21:54
date last changed
2012-10-10 09:28:53
@inproceedings{1948358,
  abstract     = {Learning an inverse kinematic model of a robot is a well studied subject. However, achieving this without information about the geometric characteristics of the robot is less investigated. In this work, a novel control approach is presented based on a recurrent neural network. Without any prior knowledge about the robot, this control strategy learns to control the iCub{\textquoteright}s robot arm online by solving the inverse kinematic problem in its control region. Because of its exploration strategy the robot starts to learn by generating and observing random motor behavior. The modulation and generalization capabilities of this approach are investigated as well.},
  author       = {Waegeman, Tim and Schrauwen, Benjamin},
  booktitle    = {Lecture Notes in Computer Science},
  editor       = {Lu, Bao-Liang and Zhang, Liqing and Kwok, James},
  isbn         = {9783642249648},
  issn         = {0302-9743},
  keyword      = {Adaptive control,Feedback control,Inverse kinematics,Neural network (NN),Reservoir computing (RC)},
  language     = {eng},
  location     = {Shanghai, PR China},
  number       = {3},
  pages        = {441--448},
  publisher    = {Springer},
  title        = {Towards learning inverse kinematics with a neural network based tracking controller},
  url          = {http://dx.doi.org/10.1007/978-3-642-24965-5\_50},
  volume       = {7064},
  year         = {2011},
}

Chicago
Waegeman, Tim, and Benjamin Schrauwen. 2011. “Towards Learning Inverse Kinematics with a Neural Network Based Tracking Controller.” In Lecture Notes in Computer Science, ed. Bao-Liang Lu, Liqing Zhang, and James Kwok, 7064:441–448. Berlin, Germany: Springer.
APA
Waegeman, T., & Schrauwen, B. (2011). Towards learning inverse kinematics with a neural network based tracking controller. In B.-L. Lu, L. Zhang, & J. Kwok (Eds.), Lecture Notes in Computer Science (Vol. 7064, pp. 441–448). Presented at the 18th International Conference on Neural Information Processing (ICONIP 2011), Berlin, Germany: Springer.
Vancouver
1.
Waegeman T, Schrauwen B. Towards learning inverse kinematics with a neural network based tracking controller. In: Lu B-L, Zhang L, Kwok J, editors. Lecture Notes in Computer Science. Berlin, Germany: Springer; 2011. p. 441–8.
MLA
Waegeman, Tim, and Benjamin Schrauwen. “Towards Learning Inverse Kinematics with a Neural Network Based Tracking Controller.” Lecture Notes in Computer Science. Ed. Bao-Liang Lu, Liqing Zhang, & James Kwok. Vol. 7064. Berlin, Germany: Springer, 2011. 441–448. Print.