Grid Based Path Planning Using CNN & Artificial Potential Field Method

Abstract:

This proposed path planning method combines cellular neural network (CNN) with artificial potential field approach. The fundamental operation based on CNN gray scale image processing and artificial potential is the additional approach for global path-planning. Every point of the environment has a potential value with respect to start and destination position. In the trajectory planning process, a minimum search of potential value of every surrounding neighbor points around a point is done and the neighbor point with the least minimum value is selected as the next location. This procedure is repeated until the goal point is reached. The advantage of using CNN based image processing with artificial potential field function in a vision system is its effectiveness in robot localization while the use of minimum potential value gives a simple yet efficient path planning method. Their feedback criterion is similar to a procedure in filtering the image and it frequently updates the information about obstacles and free path. The parallel processing properties of CNN makes the proposed method robust for real time application.

• Periodical: Applied Mechanics and Materials (Volume 392)
• Pages: 830-836
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.392.830
• Online since: September 2013
• Authors: Shamina Akter, Deok Jin Lee, Shin Taek Lim, Kil To Chong
• Keywords: Artificial Potential Field (APF), Autonomous Robot, Cellular Neural Network, Image Processing, Path-Planning

References

[1] Z. Nagy, P. Szolgay, in, Krakow, Poland, 2003, pp.181-184.

[2] T. Roska, L.O. Chua, Circuits and Systems II: Analog and Digital Signal Processing, IEEE Transactions on, Vol. 40 (1993) 163-173.

DOI: 10.1109/82.222815

[3] G.L. Cembrano, A. Rodriguez-Vasquez, S. Espejo-Meana, R. Dominguez-Castro, Int J Neural Syst, Vol. 13 (2003) 427 - 434.

[4] P. Arena, A. Basile, L. Fortuna, A. Virzi, in, 2002, pp.291-298.

[5] A. Gacsadi, T. Maghiar, V. Tiponut, in, 2002, pp.188-194.

[6] I. Gavrilut, A. Gacsadi, C. Grava, V. Tiponut, in, 2006, pp.306-311.

[7] I. Gavrilut, V. Tiponut, A. Gacsadi, in, Crete Island, Greece, 2007, pp.81-86.

[8] V. Tiponut, I. Gavrilut, C. Caleanu, A. Gacsadi, WSEAS Transactions on Circuits and Systems, Vol. 5 (2006) 805 - 812.

[9] P. Arena, L. Fortuna, M. Frasca, G. Vagliasindi, A. Basile, in, 2005, pp.5818-5821 Vol. 5816.

[10] L.O. Chua, L. Yang, Circuits and Systems, IEEE Transactions on, Vol. 35 (1988) 1273-1290.

[11] G. Linan, S. Espejo, R. Dominguez-Castro, E. Roca, A. Rodriguez-Vazquez, in, 1999, pp.61-68.

[12] C. Rekeczky, in, Analogical and Neural Computing Laboratory, Computer and Automation Institute of the Hungarian Academy of Sciences, Budapest, (1997).

[13] J. Borenstein, Y. Koren, Robotics and Automation, IEEE Transactions on, Vol. 7 (1991) 278-288.

[14] Z. Liu, M.H. Ang Jr, W.K.G. Seah, in, Manila, Philippines, (2003).