Research Article

A Parallelized Matrix-Multiplication Implementation of Neural Network for Collision Free Robot Path Planning

by  Abhishek Kumar, Ravi Bhushan Mishra
journal cover
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 69 - Issue 28
Published: May 2013
Authors: Abhishek Kumar, Ravi Bhushan Mishra
10.5120/12249-8443
PDF

Abhishek Kumar, Ravi Bhushan Mishra . A Parallelized Matrix-Multiplication Implementation of Neural Network for Collision Free Robot Path Planning. International Journal of Computer Applications. 69, 28 (May 2013), 24-29. DOI=10.5120/12249-8443

                        @article{ 10.5120/12249-8443,
                        author  = { Abhishek Kumar,Ravi Bhushan Mishra },
                        title   = { A Parallelized Matrix-Multiplication Implementation of Neural Network for Collision Free Robot Path Planning },
                        journal = { International Journal of Computer Applications },
                        year    = { 2013 },
                        volume  = { 69 },
                        number  = { 28 },
                        pages   = { 24-29 },
                        doi     = { 10.5120/12249-8443 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2013
                        %A Abhishek Kumar
                        %A Ravi Bhushan Mishra
                        %T A Parallelized Matrix-Multiplication Implementation of Neural Network for Collision Free Robot Path Planning%T 
                        %J International Journal of Computer Applications
                        %V 69
                        %N 28
                        %P 24-29
                        %R 10.5120/12249-8443
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

This paper covers the problem of Collision Free Path Planning for an autonomous robot and proposes a solution to it through the Back Propagation Neural Network. The solution is transformed into a composition of matrix-multiplication operations, which is a classic example of problems that can be efficiently parallelized. This paper finally proposes a parallel implementation of this matrix-multiplication method which, in itself, encapsulates the neural network that implements the collision free path planning for an autonomous robot.

References
  • DU Xin 1, CHEN Hua-hua 2, GU Wei-kang1/ Neural network and genetic algorithm based global path planning in a static environment, (1 Department of Information Science and Electronics Engineering, Zhejiang University, Hangzhou 310027, China)(2 School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China)
  • Youssef Bassil / Neural Network Model for Path-Planning Of Robotic Rover Systems, International Journal of Science and Technology (IJST), E-ISSN: 2224-3577, Vol. 2, No. 2, February, 2012
  • Janglová, D. / Neural Networks in Mobile Robot Motion, pp. 15-22, Inernational Journal of Advanced Robotic Systems, Volume 1 Number 1 (2004), ISSN 1729-8806.
  • Kyung Min Han, Collision Free Path Planning Algorithms for Robot Navigation Problems, A Thesis presented to the faculty of the Graduate School University of Missouri-Columbia, 2007
  • R. Glasius, A. Komoda, S. Gielen / Neural Network Dynamics for Path-planning and Obstacle Avoidance, Department of Medical Physics and Biophysics, University of Nijmegen, Geert GrootepleinNoord 21, 6525 EZ Nijmegen, The Netherlands
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

Robot Path Planning Back Propagation Neural Networks Parallelism Matrix-Multiplication

Powered by PhDFocusTM