Elimination of the Collision States of the Effectors of Industrial Robots by Application of Neural Networks

Abstract:

The article deals with the usage of methods of learning algorithms of neural networks for solving of collision states problem within multi-robotic cooperation. Nowadays, multi-robotic cooperation is a highly used method of work of two or more industrial robots. The requirements for elimination of collision states are getting more difficult when the multi-robotic system is more complicated. Methods of neural networks provide suitable tools for solving of complex cooperating problems. In the beginning of the article, we discuss the term “collision state” and the possibilities of its solving. In the following chapter, we discuss the theory of neural networks and learning algorithms, which we applied in solving of the collision states. In the final chapter, we implemented the practical verification of the model neural network in JSNN programme. It consisted of creating and learning of the training data and subsequent verification of the test data.

• Periodical: Applied Mechanics and Materials (Volume 798)
• Pages: 276-281
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.798.276
• Online since: October 2015
• Authors: Erik Prada*, Lenka Baločková, Michael Valášek
• Keywords: Collision States, Industrial Robot, Multi-Robotic Systems, Neural Networks

References

[1] L. Baločková: Metódy koordinácie manipulačných operácii v multirobotických systémoch, Dissertation thesis, Technical University of Kosice, Kosice (2014).

[2] E. Prada: Periodic and nonperiodic possibility of locomotion of redundant robotic system, Dissertation thesis, Technical University of Kosice, Kosice (2014).

[3] V. Marík a kol.: Umelá inteligence 2, Centa spol. s r. o., Brno, (1997).

[4] L. Baločková: The method for solving kinematics of an industrial robot, Applied Mechanics and Materials. Vol. 282, pp.274-28, (Trans Tech Publications, Switzerland 2014).

DOI: 10.4028/www.scientific.net/amm.282.274

[5] J. N. Pires: Industrial Robots Programming: Building Applications for the Factories of the Future, Springer, 2007, p.282.

[6] E. Prada, A. Gmiterko, L. Baločková: Notional proposal of a mechatronic system of an artificial (robotic) snake and its electromagnetic actuator, International Journal of Science Commerce and Humanities. Vol. 1, no. 8 (2013), pp.77-85.

[7] E. Prada, L. Baločková: Použitie neurónových sieti pri priamočiarej lokomócií robotického hada, Automatizácia / Robotika v teórii a praxi: 11. celoštátna konferencia s medzinárodnou účasťou (ROBTEP 2011), Košice, pp.155-160.

[8] A. Palko, J. Smrček, J. Skařupa, P. Tuleja: Robotika : technické prostriedky pre automatizáciu výrobných procesov: navrhovanie, konštrukcia, príklady riešenia, Applied Mechanics and Materials. Vol. 282 , pp.274-28.

[9] P.K. Sycara: Multiagent systems, AI magazine Volume 19, No. 2 Intelligent Agents, Summer 1998, pp.79-92 ., [online] http: /www. cs. cmu. edu/~softagents/papers/multiagentsystems. PDF.

[10] I. Virgala, M. Dovica, M. Kelemen, E. Prada, Z. Bobovský: Snake Robot Movement in the Pipe Using Concertina Locomotion, Applied Mechanics and Materials, Vol 611, p.121, (Trans Tech Publications, Switzerland 2014).

DOI: 10.4028/www.scientific.net/amm.611.121