Multirole Population of Automated Helmsmen in Neuroevolutionary Ship Handling

• Autorzy: Lacki, M.
• Języki publikacji: EN

Abstrakty

EN

This paper presents the proposal of advanced intelligent system able to simulate and demon-strate learning behavior of helmsmen in ship maneuvering. Simulated helmsmen are treated as individuals in population, which through environmental sensing learn themselves to safely navigate on restricted waters. In-dividuals are being organized in groups specialized for particular task in ship maneuvering process. Neuroev-olutionary algorithms, which develop artificial neural networks through evolutionary operations, are used in this system.

Słowa kluczowe

EN

Ship Manoeuvering; neuroevolutionary ship handling; Automated Helmsmen; Advanced Intelligent System

• Czasopismo: TransNav : International Journal on Marine Navigation and Safety of Sea Transportation
• Rocznik: 2011
• Tom: Vol. 5, no. 2
• Strony: 255--260
• Opis fizyczny: Bibliogr. 19 poz., rys.

Twórcy

autor

Lacki, M.

• Gdynia Maritime University, Gdynia, Poland

Bibliografia

• [1] Beyer, H.-G. & Schwefel, P. H. 2002. Evolution strategies – A comprehensive introduction. Natural Computing, 1(1):3–52.
• [2] Braun, H. & Weisbrod, J. 1993. Evolving feedforward neural networks. Proceedings of ANNGA93, International Conference on Artificial Neural Networks and Genetic Algorithms. Berlin: Springer.
• Chu T. C., Lin Y. C. 2003. A Fuzzy TOPSIS Method for Robot Selection, the International Journal of Advanced [3] Manufacturing Technology: 284-290,
• [4] Filipowicz, W., Łącki, M. & Szłapczyńska, J. 2005, Multicriteria decision support for vessels routing, Proceedings of ESREL’05 Conference.
• [5] Kaelbling, L. P., Littman & Moore. 1996. Reinforcement Learning: A Survey.
• [6] Kenneth, O.S., & Miikkulainen, R. 2002. Efficient Evolution of Neural Network Topologies, Proceedings of the 2002 Congress on Evolutionary Computation, Piscataway.
• [7] Kenneth, O.S. & Miikkulainen R. 2005. Real-Time Neuroevolution in the NERO Video Game, Proceedings of the IEEE 2005 Symposium on Computational Intelligence and Games, Piscataway.
• [8] Łącki, M. 2007 Machine Learning Algorithms in Decision Making Support in Ship Handling, Proceedings of TST Conference, Katowice-Ustroń, WKŁ.
• [9] Łącki, M. 2008, Neuroevolutionary approach towards ship handling, Proceedings of TST Conference, Katowice-Ustroń, WKŁ.
• [10] Łącki, M. 2009a, Speciation of population in neuroevolution-ary ship handling, Marine Navigation and Safety of Sea Transportation, CRC Press/Balkema, Taylor & Francis Group, Boca Raton – London - New York - Leiden, p. 541-545.
• [11] Łącki, M. 2009b, Ewolucyjne sieci NEAT w sterowaniu statkiem, Inżynieria Wiedzy i Systemy Ekspertowe, Akade-micka Oficyna Wydawnicza EXIT, Warszawa, p. 535-544.
• [12] Łącki, M. 2010a, Wyznaczanie punktów trasy w neuroewolucyjnym sterowaniu statkiem. Logistyka, No 6.
• [14] Łącki, M. 2010b, Model środowiska wieloagentowego w neroewolucyjnym sterowaniu statkiem. Zeszyty Naukowe Akademii Morskiej w Gdyni, No 67, p. 31-37.
• [14] Spears, W. 1995. Speciation using tag bits. Handbook of Evolutionary Computation. IOP Publishing Ltd. and Oxford University Press.
• [15] Stanley, K. O. & Miikkulainen, R. 2002. Efficient reinforce-ment learning through evolving neural network topologies. Proceedings of the Genetic and Evolutionary Computation. Conference (GECCO-2002). San [16] Francisco, CA: Morgan Kaufmann.
• Stanley, K. O. & Miikkulainen, R. 2005. Real-Time Neuroevolution in the NERO Video Game, Proceedings of the IEEE 2005 Symposium on Computational Intelligence and Games, Piscataway.
• [17] Sutton, R. 1996. Generalization in Reinforcement Learning: Successful Examples Using Sparse Coarse Coding. Touretzky, D., Mozer, M., & Hasselmo, M. (Eds.), Neural Information Processing Systems 8.
• [18] Sutton, R. & Barto, A. 1998. Reinforcement Learning: An Introduction.
• [19] Tesauro, G. 1995. Temporal Difference Learning and TD-Gammon, Communications of the Association for Computing Machinery, vol. 38, No. 3.