Tuesday , August 14 2018

Optimization of Robotic Mobile Agent Navigation

Sándor Tihamér Brassai1,2, Barna Iantovics2, Călin Enăchescu2
1 Petru Maior University
1 Nicolae Iorga Street, Târgu Mureş
2 Sapientia University
şos. Sighişoarei 1.C., Corunca/Târgu Mureş, Romania

Abstract: The traveling salesman problem (TSP) has many applications in economy, transport logic [1] etc. It also has a wide range of applicability in the mobile robot path planning optimization [2]. The paper presents research result of solving the path planning subproblem of the navigation of an intelligent autonomous mobile robotic agent. Collecting objects by a mobile robotic agent is the final problem that is intended to be solved. For the robotic mobile agent’s path planning is used an unsupervised neural network that can find a closely optimal path between two points in the agent’s working area. We have considered a modification of the criteria function of the winner neuron selection. Simulation results are discussed at the end of the paper. The next future development is the hardware implementation of the self-organizing map with real time functioning.

Keywords: Robotic mobile agent; neural network; unsupervised learning; computational intelligence.

>>Full text
CITE THIS PAPER AS:
Sándor Tihamér BRASSAI, Barna IANTOVICS, Călin ENĂCHESCU, Optimization of Robotic Mobile Agent Navigation, Studies in Informatics and Control, ISSN 1220-1766, vol. 21 (4), pp. 403-412, 2012.

1. Introduction

Robotic mobile agents have a wide range of applications in different areas [3], such as: access dangerous areas to humans, underwater explorations, monitoring the environment, painting and de-painting applications [26]. In our research, as mobile agent a robotic mobile agent is considered. The main properties of the mobile agent are: the intelligence in operation, autonomy, reactivity and mobility. Many scientists are working on finding new solutions for different subsections of robotic mobile agent and multi-agent [4] applications such as [3] navigation, localization, optimal path planning, path following [5] object detection, movement and modelling [6] of the mobile robots with multiple implementation solutions [7]. In this paper we will focus on path planning optimization of the mobile agent using neural networks.

We will give solutions for:

  • a TSP and a modified TSP problem solving when the agent does not have to get back to the starting point.
  • Finding a closely optimal path from the resolved TSP. For solving the TSP a Kohonen map was used with a proposed cost function in the winner neuron’s selection. In the following sections, the TSP problem, the network structure and training, and results with the resolved TSP with Kohonen map and optimization of path planning between a starting node and a target node on the map will be presented.

The paper is organized as follows: Section 2 discuss the problem that we intend to solve and presents some existent solutions for TSP solving; in Section 3 our proposal for path finding is presented with preliminaries of self-organizing map architecture, a modified solution for TSP solving, and the optimal path finding; Section 4 presents the conclusions of the research and the future research direction.

References:

  1. FILIP, E., M. OTAKAR, The Travelling Salesman Problem and its Application in Logistic Practice, WSEAS Transactions on Business and Economics, Issue 4, Volume 8, 2011, pp. 163-173
  2. RAJA, R., S. PUGAZHENTHI, Optimal Path Planning of Mobile Robots: A Review, International Journal of Physical Sciences, 2012, pp. 1314-1320
  3. SIEGWART, R., I. R. NOURBAKHSH, D. SCARAMUZZA, Introduction to Autonomous Mobile Robots, The MIT Press Cambridge, Massachusetts, London, England, 2011.
  4. HERNANDEZ-MARTINEZ, E. G., E. ARANDA-BRICAIRE, Decentralized Formation Control of Multi-agent Robot Systems based on Formation Graphs, Studies in Informatics and Control, vol. 21(1), 2012, pp. 7-16.
  1. CHATTI, A., P. BORNE, M. BENREJEB, On the Use of Neural Techniques for Path Following Control of a Car-like Mobile Robot, Studies in Informatics and Control, Vol. 14(4), 2005, p. 221.
  2. LATORRE, H., K. HARISPE, R. SALINAS, G. H. LEFRANC, Ontology Model of a Robotics Agents Community, Int. J. of Comp., Comm. & Ctrl., ISSN 1841-9836, Vol. VI (1), 2011, pp. 125-133.
  3. BRAUNL, T., Embedded Robotics: Mobile Robot Design and Applications with Embedded Systems, Springer-Verlag Berlin, Heidelberg, New York, 2003.
  4. MATAI, R., S. P. SINGH, M. L. MITTAL, Travelling Salesman Problem: an Overview of Applications, Formulations, and Solution Approaches, InTech, 11/2010; ISBN: 978-953-307-426-
  5. PARKER, L. E., Path Planning and Motion Coordination in Multiple Mobile Robot Teams, Encyclopedia of Complexity and System Science, Springer, 2009.
  6. JIANN-HORNG, L., H. LI-REN, Chaotic Bee Swarm Optimization Algorithm for Path Planning of Mobile Robots, Proc. 10th WSEAS Intl. Conf. on Ev. Comp., Prague, Czech Republic, 2009, pp. 84-89.
  7. PICHPIBUL, T., R. KAWTUMMACHAI, New Enhancement for Clarke-Wright Savings Algorithm to Optimize the Capacitated Vehicle Routing Problem, Eur. J. of Sc. Res., Vol. 78(1), 2012, pp.119-134, ISSN 1450-216X
  8. ZHAO, J., X. FU, Y. JIANG, An Improved Ant Colony Optimization Algorithm for Mobile Robot Path Planning, 3rd Intl. W-shop on Intell. Sys. and App. (ISA), 28-29 May 2011.
  9. PINTEA, C. M., P. C. Pop, D., DUMITRESCU, An Ant-based Technique for the Dynamic Generalized Travelling, Salesman Problem, Proc. 7th WSEAS Intl. Conf. on Sys. Theory and Sc. Comp., Athens, Greece, Aug., 2007, pp. 255-259
  10. NOUARA A., C. MOHAMED, Mobile Robots Path Planning using Genetic Algorithms, ICAS 2011, The Seventh International Conference on Autonomic and Autonomous Systems, pp 111-115
  11. KAO-TING, H., L. JING-SIN, C. YAU-ZEN, A Comparative Study of Smooth Path Planning for a Mobile Robot by Evolutionary Multi-objective Optimization, Proc. 2007 IEEE Intl. Sym. on Comp. Intel. in Rob. and Autom.
  12. YOGITA G.,G. KUSUM, Artificial Intelligence in Robot Path Planning, Intl. J. of Soft Comp. and Eng. (IJSCE), Vol. 2(2), 2012.
  13. SIVARAM, K. M. P.,S. RAJASEKARAN, A Neural Network based Path Planning Algorithm for Extinguishing Forest Fires, IJCSI Intl. J. of Comp. Sc. Iss., Vol. 9(2), No 2, 2012.
  14. SITI, N., A. P. PUTRA, RENDYANSAH, Intelligent Navigation in Unstructured Environment by using Memory-Based Reasoning in Embedded Mobile Robot, Eur. J. of Sc. Res. ISSN 1450-216X Vol. 72(2), 2012, pp. 228-244.
  15. KOHONEN, T., Self-Organizing Maps, Third Edition, Springer, 2001,
  16. BRASSAI, S. T., L. BAKÓ, G. PANA, Şt. DAN, Neural Control Based on RBF Network implemented on FPGA, 11th Intl. Conf. on Opt. of El. and Elec. Eq., OPTIM 2008, pp.41-46.
  17. BRASSAI, S. T., L. BAKÓ, Visual Trajectory Control of a Mobile Robot Using FPGA Implemented Neural Network, Pollack, Intl. J. for Eng. and Inf. Sc., Vol. 4(3), 2009, pp. 129-142.
  18. BRASSAI, L. D., L. BAKÓ, Hardware Implementation of CMAC based Artificial Network with Process Control Application, Trans. on El. and Comm., Sc. Bul., “Politehnica” Univ. of Timisoara, 2004, p209-213, ISSN 1583-3380.
  19. BRASSAI, S. T., L. BAKÓ, Şt. DAN, FPGA Parallel Implementation of CMAC Type Neural Network with on Chip Learning, SACI 2007, Budapest Tech, Hungary, 2007, 111-115, ISBN: 142441234X
  20. BRASSAI, S. T., L. BAKÓ, Hardware Implementation of CMAC Type Neural Network on FPGA for Command Surface Approximation, J. of Ap. Sc. Budapest Tech Hungary, Vol. 4, No. 3, 2007, ISSN 1785-8860
  21. BRASSAI. S. T., Neuroadaptive Systems Based on FPGA Circuits with Application in Automatic Control, Phd thesis at Transilvania University from Brasov, 2008 Brassai Macro Conference.
  22. BRAMSON, B., New Applications for Mobile Robots, Robotics Online, 2011.

https://doi.org/10.24846/v21i4y201206