Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm

Emre Sariyildiz, Kemal Ucak, Gulay Oke, Hakan Temeltas, Kouhei Ohnishi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

In this paper, inverse differential kinematic modeling is performed for a 7-DOF (Degrees of Freedom) redundant robot arm. Two intelligent identification methods, namely Artificial Neural Networks (ANN) and Support Vector Regression (SVR) are used for modeling. The main strengths of SVR over ANN are that it doesn't get stuck at local minima and it has powerful generalization abilities with very few training data. An important problem in inverse kinematic solutions are the singularities which are points in the operational space where manipulator Jacobian is not invertible. In this paper, simulations are performed on a PA-10 model, to compare the modeling performances attained by ANN and SVR. It has been observed that SVR outperforms ANN in inverse differential kinematic modeling. Training data is obtained using direct differential kinematic equations of the manipulator and data points close to singularities have been discarded.

Original languageEnglish
Title of host publicationINISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications
DOIs
Publication statusPublished - 2012
EventInternational Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2012 - Trabzon, Turkey
Duration: 2012 Jul 22012 Jul 4

Other

OtherInternational Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2012
CountryTurkey
CityTrabzon
Period12/7/212/7/4

Fingerprint

Inverse kinematics
Robots
Neural networks
Kinematics
Manipulators
Degrees of freedom (mechanics)

Keywords

  • Artificial Neural Networks
  • Redundancy
  • Robot Arm
  • Singularity
  • Support Vector Machine
  • Trajectory Tracking

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications

Cite this

Sariyildiz, E., Ucak, K., Oke, G., Temeltas, H., & Ohnishi, K. (2012). Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm. In INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications [6247033] https://doi.org/10.1109/INISTA.2012.6247033

Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm. / Sariyildiz, Emre; Ucak, Kemal; Oke, Gulay; Temeltas, Hakan; Ohnishi, Kouhei.

INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications. 2012. 6247033.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sariyildiz, E, Ucak, K, Oke, G, Temeltas, H & Ohnishi, K 2012, Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm. in INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications., 6247033, International Symposium on INnovations in Intelligent SysTems and Applications, INISTA 2012, Trabzon, Turkey, 12/7/2. https://doi.org/10.1109/INISTA.2012.6247033
Sariyildiz E, Ucak K, Oke G, Temeltas H, Ohnishi K. Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm. In INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications. 2012. 6247033 https://doi.org/10.1109/INISTA.2012.6247033
Sariyildiz, Emre ; Ucak, Kemal ; Oke, Gulay ; Temeltas, Hakan ; Ohnishi, Kouhei. / Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm. INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications. 2012.
@inproceedings{9ca859f0e12c4ebaa55bb15e9626fce7,
title = "Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm",
abstract = "In this paper, inverse differential kinematic modeling is performed for a 7-DOF (Degrees of Freedom) redundant robot arm. Two intelligent identification methods, namely Artificial Neural Networks (ANN) and Support Vector Regression (SVR) are used for modeling. The main strengths of SVR over ANN are that it doesn't get stuck at local minima and it has powerful generalization abilities with very few training data. An important problem in inverse kinematic solutions are the singularities which are points in the operational space where manipulator Jacobian is not invertible. In this paper, simulations are performed on a PA-10 model, to compare the modeling performances attained by ANN and SVR. It has been observed that SVR outperforms ANN in inverse differential kinematic modeling. Training data is obtained using direct differential kinematic equations of the manipulator and data points close to singularities have been discarded.",
keywords = "Artificial Neural Networks, Redundancy, Robot Arm, Singularity, Support Vector Machine, Trajectory Tracking",
author = "Emre Sariyildiz and Kemal Ucak and Gulay Oke and Hakan Temeltas and Kouhei Ohnishi",
year = "2012",
doi = "10.1109/INISTA.2012.6247033",
language = "English",
isbn = "9781467314466",
booktitle = "INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications",

}

TY - GEN

T1 - Support vector regression based inverse kinematic modeling for a 7-DOF redundant robot arm

AU - Sariyildiz, Emre

AU - Ucak, Kemal

AU - Oke, Gulay

AU - Temeltas, Hakan

AU - Ohnishi, Kouhei

PY - 2012

Y1 - 2012

N2 - In this paper, inverse differential kinematic modeling is performed for a 7-DOF (Degrees of Freedom) redundant robot arm. Two intelligent identification methods, namely Artificial Neural Networks (ANN) and Support Vector Regression (SVR) are used for modeling. The main strengths of SVR over ANN are that it doesn't get stuck at local minima and it has powerful generalization abilities with very few training data. An important problem in inverse kinematic solutions are the singularities which are points in the operational space where manipulator Jacobian is not invertible. In this paper, simulations are performed on a PA-10 model, to compare the modeling performances attained by ANN and SVR. It has been observed that SVR outperforms ANN in inverse differential kinematic modeling. Training data is obtained using direct differential kinematic equations of the manipulator and data points close to singularities have been discarded.

AB - In this paper, inverse differential kinematic modeling is performed for a 7-DOF (Degrees of Freedom) redundant robot arm. Two intelligent identification methods, namely Artificial Neural Networks (ANN) and Support Vector Regression (SVR) are used for modeling. The main strengths of SVR over ANN are that it doesn't get stuck at local minima and it has powerful generalization abilities with very few training data. An important problem in inverse kinematic solutions are the singularities which are points in the operational space where manipulator Jacobian is not invertible. In this paper, simulations are performed on a PA-10 model, to compare the modeling performances attained by ANN and SVR. It has been observed that SVR outperforms ANN in inverse differential kinematic modeling. Training data is obtained using direct differential kinematic equations of the manipulator and data points close to singularities have been discarded.

KW - Artificial Neural Networks

KW - Redundancy

KW - Robot Arm

KW - Singularity

KW - Support Vector Machine

KW - Trajectory Tracking

UR - http://www.scopus.com/inward/record.url?scp=84866605723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84866605723&partnerID=8YFLogxK

U2 - 10.1109/INISTA.2012.6247033

DO - 10.1109/INISTA.2012.6247033

M3 - Conference contribution

AN - SCOPUS:84866605723

SN - 9781467314466

BT - INISTA 2012 - International Symposium on INnovations in Intelligent SysTems and Applications

ER -