Speciation of Population in Neuroevolutionary Ship Handling

ABSTRACT: This paper presents the idea of using machine learning techniques to simulate and demonstrate learning behavior in ship maneuvering. Simulated helmsman is treated as an individual in population, which through environmental sensing learns itself to navigate through restricted waters selecting an optimum trajectory. Learning phase of the task is to observe current situation and choose one of the available actions. The individual improves his fitness function with reaching destination and decreases its value for hitting an obstacle. Neuroevolutionary approach is used to solve this task. Speciation of population is proposed as a method to secure innovative solutions.

KEYWORDS: Ship Handling, Machine Learning Techniques, Restricted Waters, Neuroevolutionary Ship Handling, Multi-Attribute Decision Making (MADM), Optimum Trajectory, Neuro Evolution of Augmenting Topologies (NEAT), Manoeuvring

REFERENCES

Beyer, H.-G. & Paul Schwefel, H. 2002. Evolution strategies – A comprehensive introduction. Natural Computing, 1(1):3–52.

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 Manufacturing Technology: 284-290,

Filipowicz, W., Łącki, M. & Szłapczyńska, J. 2005, Multicriteria decision support for vessels routing, Proceedings of ESREL’05 Conference.

Kaelbling, L. P., Littman & Moore. 1996. Reinforcement Learning: A Survey.

Łącki M., 2007 Machine Learning Algorithms in Decision Making Support in Ship Handling, Proceedings of TST Conference, Katowice-Ustroń, WKŁ.

Łącki, M. 2008, Neuroevolutionary approach towards ship handling, Proceedings of TST Conference, Katowice-Ustroń, WKŁ.

Spears, W. 1995. Speciation using tag bits. Handbook of Evolutionary Computation. IOP Publishing Ltd. and Oxford University Press.

Stanley, K. O. & Miikkulainen, R. 2002. Efficient reinforcement learning through evolving neural network topologies. Proceedings of the Genetic and Evolutionary Computation. Conference (GECCO-2002). San 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

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.

Sutton, R. & Barto, A. 1998. Reinforcement Learning: An Introduction.

Tesauro, G. 1995. Temporal Difference Learning and TD-Gammon, Communications of the Association for Computing Machinery, vol. 38, No. 3.

Citation note:

Łącki M.: Speciation of Population in Neuroevolutionary Ship Handling. TransNav, the International Journal on Marine Navigation and Safety of Sea Transportation, Vol. 4, No. 2, pp. 211-216, 2010

BibTeX EndNote