Artificial intelligence-based path finding in land war game

Document Type : Original Article

Authors

1 Member of Dafos Aja faculty, Tehran, Iran.

2 Department of science and technology, AJA Command and Staff University, Tehran. Iran.

3 Associate Professor, Faculty of Electrical Engineering, Shahid Sattari University of Aeronautical Sciences and Technology, Tehran, Iran.

Abstract

The war game is used in the world as one of the decision-making and decision-making practice methods of military commanders, and if this simulation is prepared with artificial intelligence tools, it will increase the decision-making power and have a significant effect on reducing costs and preventing wastage of resources. One of the items used in war game systems, which is the subject of this article, is the path finding. In this regard, first A* path finding was investigated and then its disadvantages were improved by combining the hierarchical method. Then path finding with reinforcement learning algorithm with data pre-processing as innovative methods in order to match the maps has been studied before performing the path finding phase. In the following, path finding with reinforcement learning has been investigated in a hierarchical manner. Also, the time and speed of different units have been applied in path finding and its results have been analyzed.

Keywords

Main Subjects

References

[1]فرخی، راحله. (1399). حل مدل مسیریابی وسایل حمل مواد خطرناک مبتنی بر کاهش ریسک با استفاده از رویکرد سلسله‌مراتبی، دانشگاه علم و صنعت ایران.
[2] K. D. Forbus, J. V. Mahoney, and K. Dill, (2002). How qualitative spatial reasoning can improve strategy game AIs, IEEE Intelligent Systems, vol. 17, no. 4, pp. 25–30.
[3] E. Bethke, (2003). Game Development and Production, Wordware, Plano, Tex, USA.
[4] K. Forbus, (1996). Qualitative reasoning, in CRC Handbook of Computer Science and Engineering, pp. 715–733, CRC Press, Boca Raton, Fla, USA.
[5] A. G. Cohn, (1997). Qualitative spatial representation and reasoning techniques, in Proceedings of the 21st Annual German Conference on Artificial Intelligence: Advances in Artificial Intelligence (KI ’97). vol. 1303 of Lecture Notes in Computer Science, pp. 1–30, Springer, Freiburg, Germany.
[6] A. Botea, M. Muller, and J. Schaeffer, (2004). Near optimal hierarchi- cal path-finding, Journal of Game Development, vol. 1, no. 1, pp. 7–28.
[7] S. Rabin. (2000). A∗ speed optimizations, in Game Programming Gems, M. DeLoura, Ed. , pp. 272–287, Charles River Media, Rockland, Mass, USA.
[8] R. S. Sutton and A. G. Barto, (1998). Reinforcement Learning: An Introduction, MIT Press, Cambridge, Mass, USA.
[9] I. Millington. (2006). Artificial Intelligence for Games, Morgan Kauf- mann, San Mateo, Calif, USA.
[10] D, Michie, D. J. Spiegelhalter, C. C. Taylor. (1994). Machine Learning, Neural and Statistical Classification, Prentice Hall, Upper Saddle River, NJ, USA.    
Iranian Journal of Wargaming
Volume 5, Issue 10 - Serial Number 10
September 2022
Pages 25-46

Files

Share

How to cite

Statistics