An adaptive island model of population for neuroevolutionary ship handling

• Autorzy: Łącki Mirosław

Identyfikatory

DOI

10.2478/pomr-2021-0056

• Języki publikacji: EN

Abstrakty

EN

This study presents a method for the dynamic value assignment of evolutionary parameters to accelerate, automate and generalise the neuroevolutionary method of ship handling for different navigational tasks and in different environmental conditions. The island model of population is used in the modified neuroevolutionary method to achieve this goal. Three different navigational situations are considered in the simulation, namely, passing through restricted waters, crossing with another vessel and overtaking in the open sea. The results of the simulation examples show that the island model performs better than a single non-divided population and may accelerate some complex and dynamic navigational tasks. This adaptive island-based neuroevolutionary system used for the COLREG manoeuvres and for the finding safe ship’s route to a given destination in restricted waters increases the accuracy and flexibility of the simulation process. The time statistics show that the time of simulation of island NEAT was shortened by 6.8% to 27.1% in comparison to modified NEAT method.

Słowa kluczowe

EN

artificial neural networks; evolutionary algorithms; neuroevolution; ship movement control; ship manoeuvring

• Wydawca: Gdańsk University of Technology, Faculty of Ocean Engineering & Ship Technology
• Czasopismo: Polish Maritime Research
• Rocznik: 2021
• Tom: nr 4
• Strony: 142--150
• Opis fizyczny: Bibliogr. 24 poz., rys., tab.

Twórcy

autor

Łącki Mirosław

• Gdynia Maritime University, Morska 81/87, 81-225 Gdynia, Poland

Bibliografia

• 1. D. Whitley, S. Rana, and R. Heckendorn, “The Island Model Genetic Algorithm: On Separability, Population Size and Convergence,” Journal of Computing and Information Technology, vol. 7, 1998.
• 2. H. M. Pandey, A. Chaudhary, and D. Mehrotra, “A comparative review of approaches to prevent premature convergence in GA,” Applied Soft Computing, vol. 24, pp. 1047–1077, 2014, doi: https://doi.org/10.1016/j.asoc.2014.08.025.
• 3. E. Alba and J. M. Troya, “An analysis of synchronous and asynchronous parallel distributed genetic algorithms with structured and panmictic Islands,” in Parallel and Distributed Processing, Berlin, Heidelberg, 1999, pp. 248–256.
• 4. A. Hoang et al., “A review on application of artificial neural network (ANN) for performance and emission characteristics of diesel engine fueled with biodiesel-based fuels,” Sustainable Energy Technologies and Assessments, Jun. 2021, doi: 10.1016/j.seta.2021.101416.
• 5. S. L. Boung Yew and K. K. Kee, “Artificial Neural Network Back-Propagation Based Decision Support System for Ship Fuel Consumption Prediction,” 2018. doi: 10.1049/cp.2018.1306.
• 6. W. Tarełko and K. Rudzki, “Applying artificial neural networks for modelling ship speed and fuel consumption,” Neural Computing & Applications, vol. 32, pp. 17379–17395, 2020. doi: 10.1007/s00521-020-05111-2.
• 7. J. Liu, G. Shi, and K. Zhu, “Vessel Trajectory Prediction Model Based on AIS Sensor Data and Adaptive Chaos Differential Evolution Support Vector Regression (ACDESVR),” Applied Sciences, vol. 9, p. 2983, 2019, doi: 10.3390/app9152983.
• 8. K. Bobkowska and I. Bodus-Olkowska Izabela, “Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification,” Polish Maritime Research, vol. 27, pp. 170–178, 2020. doi: 10.2478/pomr-2020-0077
• 9. G. Li, B. Kawan, H. Wang, and H. Zhang, “Neural-networkbased modelling and analysis for time series prediction of ship motion,” Ship Technology Research, vol. 64, 2017, doi: 10.1080/09377255.2017.1309786.
• 10. T. Niksa-Rynkiewicz and A. Witkowska, “Analysis of impact of ship model parameters on changes of control quality index in ship dynamic positioning system,” Polish Maritime Research, vol. 26, no. 1(101), pp. 6–14, 2019. doi: 10.2478/pomr-2019-0001
• 11. J. Lisowski, “Computational Intelligence in Marine Control Engineering Education,” Polish Maritime Research, vol. 28, no. 1, pp. 163–172, 2021, doi: doi:10.2478/pomr-2021-0015.
• 12. R. Lopes, R. Pedrosa Silva, F. Campelo, and F. Guimaraes, “A Multi-agent Approach to the Adaptation of Migration Topology in Island Model Evolutionary Algorithms,” in Proceedings - Brazilian Symposium on Neural Networks, SBRN, 2012, pp. 160–165. doi: 10.1109/SBRN.2012.36.
• 13. P. Garcia-Sanchez, J. Ortega, J. Gonzalez, P. A. Castillo, and J. J. Merelo, “Distributed multi-objective evolutionary optimization using island-based selective operator application,” Applied Soft Computing, vol. 85, p. 105757, 2019, doi: https://doi.org/10.1016/j.asoc.2019.105757.
• 14. E. Cantu-Paz and D. E. Goldberg, “Are Multiple Runs of Genetic Algorithms Better than One?,” in Genetic and Evolutionary Computation — GECCO 2003, Berlin, Heidelberg, 2003, pp. 801–812.
• 15. R. Śmierzchalski, Ł. Kuczkowski, P. Kolendo, and B. Jaworski, “Distributed Evolutionary Algorithm for Path Planning in Navigation Situation,” TransNav, the International Journal on Marine Navigation and Safety of Sea Transportation, vol. 7, pp. 293–300, 2013, doi: 10.12716/1001.07.02.17.
• 16. A. Skakovski and P. Jędrzejowicz, “An island-based differential evolution algorithm with the multi-size populations,” Expert Systems with Applications, vol. 126, pp. 308–320, 2019, doi: https://doi.org/10.1016/j.eswa.2019.02.027.
• 17. J. Szlapczynska and R. Szlapczynski, “Preference-based evolutionary multi-objective optimization in ship weather routing,” Applied Soft Computing, vol. 84, p. 105742, 2019, doi: https://doi.org/10.1016/j.asoc.2019.105742.
• 18. L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement Learning: A Survey,” Journal of Artificial Intelligence Research, vol. cs.AI/9605, pp. 237–285, 1996, doi: 10.1613/jair.301.
• 19. R. Maeda and M. Mimura, “Automating post-exploitation with deep reinforcement learning,” Computers & Security, vol. 100, p. 102108, 2021, doi: https://doi.org/10.1016/j.cose.2020.102108.
• 20. R. De Nardi, J. Togelius, O. E. Holland, and S. M. Lucas, “Evolution of Neural Networks for Helicopter Control: Why Modularity Matters,” Evolutionary Computation, 2006. CEC 2006. IEEE Congress on, pp. 1799–1806, 2006, doi: citeulike-article-id:4142097.
• 21. N. T. Siebel and G. Sommer, “Evolutionary reinforcement learning of artificial neural networks,” International Journal of Hybrid Intelligent Systems - Hybridization of Intelligent Systems, vol. 4, pp. 171–183, 2007.
• 22. K. O. Stanley and M. Risto, “Efficient Reinforcement Learning Through Evolving Neural Network Topologies,” presented at the Proceedings of the Genetic and Evolutionary Computation Conference, 2002.
• 23. T. I. Fossen, Guidance and control of ocean vehicles. Chichester, UK: Wiley, 1994.
• 24. R. Zaccone, M. Martelli, and M. Figari, “A COLREGCompliant Ship Collision Avoidance Algorithm,” Jun. 2019, pp. 2530–2535. doi: 10.23919/ECC.2019.8796207.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).