Abstract
It is proposed to use evolutionary programming to generate finite state machines (FSMs) for controlling objects with complex behavior. The well-know approach in which the FSM performance is evaluated by simulation, which is typically time consuming, is replaced with comparison of the object’s behavior controlled by the FSM with the behavior of this object controlled by a human. A feature of the proposed approach is that it makes it possible to deal with objects that have not only discrete but also continuous parameters. The use of this approach is illustrated by designing an FSM controlling a model aircraft executing a loop-the-loop maneuver.
Similar content being viewed by others
References
N. I. Polikarpova and A. A. Shalyto, Automata-Based Programming (Piter, St. Petersburg, 1991) [in Russian], http://is.ifmo.ru/books/-book.pdf
A. A. Shalyto, SWITCH-Technology. Algorithmization and Programming Logic Control Systems (Nauka, St. Petersburg, 1998) [in Russian].
P. Angeline and J. Pollack, “Evolutionary module acquisition,” in Proc. of the Second Annual Conf. on Evolutionary Programming (MIT Press, Cambridge, 1993), pp. 154–163. http://www.demo.cs.brandeis.edu/papers/ep93.pdf
D. Jefferson, R. Collins, C. Cooper, et al., “The genesys system: Evolution as a theme in artificial life,” in Proc. of the Second Conf. on Artificial Life (Addison-Wesley, 1992), pp. 549–578. www.cs.ucla.edu/~dyer/Papers/AlifeTracker/Alife91Jefferson.html
F. N. Tsarev and A. A. Shalyto, “The use of genetic programming for generating a finite state machine in the smart ant problem,” in Proc. of the 4th Int. Conf. on Integrated Models and Soft Computations in Artificial Intelligence (Fizmatlit, Moscow, 2007), pp. 50–597. http://is.ifmo.ru/genalg/-ant-ga.pdf
“Genetic programming technology for the generation of finite state machines controlling systems with complex behavior,” Intermediate Report on Experimental Studies, St. Petersburg State University of Information Technologies, Mechanics, and Optics, St Petersburg, 2008. http://is.ifmo.ru/genalg/-2007-03-report-genetic.pdf.
D. A. Parashchenko, F. N. Tsarev, and A. A. Shalyto, “A technology for simulating a class of multiagent systems based on automata-based programming using the game of competing flying saucers as an example,” Project Documents, St. Petersburg State University of Information Technologies, Mechanics, and Optics, St Petersburg, 2006. http://is.ifmo.ru/unimod-projects/plates
A. Coates, P. Abbeel, and A. Y. Ng, “Learning for control from multiple demonstrations,” in Proc. 25th Int. Conf. on Machine Learning, Helsinki, 2008, pp. 144–151.
L. A. Gladkov, V. V. Kureichik, and V. M. Kureichik, Genetic Algorithms (Fizmatlit, Moscow, 2006) [in Russian].
S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach (Prentice Hall, Upper Saddle River, N.J., 2003; Vil’yams, Moscow, 2003).
J. R. Koza, Genetic Programming: On the Programming of Computers by Means of Natural Selection (MIT Press, Cambridge, (1992).
V. M. Kureichik, “Genetic algorithms: State of the art, problems, and perspectives,” J. Comput. Syst. Sci. Int. 38, 137–152 (1999).
V. M. Kureichik and S. I. Rodzin, “Evolutionary algorithms: Genetic programming,” J. Comput. Syst. Sci. Int. 41, 123–132 (2002).
N. I. Polikarpova, V. N. Tochilin, and A. A. Shalyto, “Method of reduced tables for generation of automata with a large number of input variables based on genetic programming,” J. Comput. Syst. Sci. Int. 49, 265–282 (2010).
F. N. Tsarev, “A method for constructing control finite state machines based on test examples using genetic programming,” Inform.-Upravl. Sist., No. 5, 31–36 (2010).
Author information
Authors and Affiliations
Corresponding author
Additional information
Original Russian Text © A.V. Aleksandrov, S.V. Kazakov, A.A. Sergushichev, F.N. Tsarev, A.A. Shalyto, 2013, published in Izvestiya Akademii Nauk. Teoriya i Sistemy Upravleniya, 2013, No. 3, pp. 85–100.
Rights and permissions
About this article
Cite this article
Aleksandrov, A.V., Kazakov, S.V., Sergushichev, A.A. et al. The use of evolutionary programming based on training examples for the generation of finite state machines for controlling objects with complex behavior. J. Comput. Syst. Sci. Int. 52, 410–425 (2013). https://doi.org/10.1134/S1064230713020020
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1064230713020020