Skip to main content
SpringerLink
Log in

Designing high-level decision making systems based on fuzzy if–then rules for a point-to-point car racing game

  • Focus
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

In this paper, fuzzy rule-based systems are applied to a point-to-point car racing game. In the point-to-point car racing game, two car agents compete with each other for taking waypoints. There are three waypoints in the car racing field, each of which is assigned a number that indicates the order to take. The control process of car agents is modeled as a non-holonomic system where there are two input variables (acceleration and steering) for controlling the position, angle and velocity of the car agents. Fuzzy rule-based systems are used to make a high-level decision where the target waypoint to take is determined. Since a fuzzy rule-based system for the high-level decision making is generated in the manner of supervised learning, a set of training patterns should be given for the construction of the fuzzy rule-based systems. In this paper we examine two methods to obtain such a set of training patterns. We also examine two representations of input vectors for the fuzzy rule-based systems. We discuss the effect of obtained training patterns and the input representation on the performance of the fuzzy rule-based systems. After discussing and analyzing the experimental results, we present an adaptive framework of fuzzy rule-based systems. The performance of adaptive fuzzy rule-based systems is then examined based on the results of their non-adaptive version. A series of computational experiments are performed to show the learning ability of the adaptive fuzzy rule-based systems.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Similar content being viewed by others

References

  • Agapitos A, Togelius J, Lucas SM (2007) Evolving controllers for simulated car racing using object oriented genetic programming. In: Proceedings of the 9th annual conference on Genetic and evolutionary computation. ACM, London, pp 1543–1550

  • Araki N, Yoshida K, Tsuruoka Y, Tsujii J (2007) Move prediction in go with the maximum entropy method. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 189–195

  • Ashlock DA (2007) Cooperation in prisoner’s dilemma on graphs. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 48–55

  • Chen W-Y, Payandeh S (2007) Micro robot hockey simulator—game engine design. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 9–16

  • DeLooze LL, Downey J (2007) Bridge bidding with imperfect information. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 368–373

  • Ghoneim A, Abbass H, Barlow M (2007) Information sharing in the iterated prisoner’s dilemma game. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 56–62

  • Ishibuchi H, Nozaki K, Tanaka H (1992) Distributed representation of fuzzy rules and its application to pattern classification. Fuzzy Sets Syst 52:21–32

    Article  Google Scholar 

  • Kim K-J, Choi H, Cho S-B (2007) Hybrid of evolution and reinforcement learning for othello players. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 203–209

  • Leigh R, Louis SJ, Miles C (2007) Using a genetic algorithm to explore a*-like pathfinding algorithms. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 72–79

  • Marques H, Togelius J, Kogutowska M, Holland O, Lucas SM (2007) Sensorless but not senseless: prediction in evolutionary car racing. In: Artificial life, 2007. ALIFE ’07. IEEE Symposium on, pp 370–377

  • Mayer HA (2007) Board representations for neural go players learning by temporal difference. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 183–188

  • McFarlin DS, Todd PM (2007) Evolving a better adversary: a case study in a german castle. In: Artificial life, 2007. ALIFE ’07. IEEE Symposium on, pp 229–235

  • Miles C, Quiroz J, Leigh R, Louis SJ (2007) Co-evolving influence map tree based strategy game players. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 88–95

  • Nakashima T, Udo M, Ishibuchi H (2003a) A fuzzy reinforcement learning for a ball interception problem. Pages in CD–ROM (8 pages), Padova, Italy

  • Nakashima T, Udo M, Ishibuchi H (2003b) Implementation of fuzzy q-learning for a soccer agent, St. Louis, USA, pp 533–536

  • Nakashima T, Takatani M, Udo M, Ishibuchi H (2004) An evolutionary approach for strategy learning in robocup soccer, Den Hague, Netherlands, pp 2023–2028

  • Nakashima T, Takatani M, Udo M, Ishibuchi H, Nii M (2005) Performance evaluation of an evolutionary method for robocup soccer strategies. Pages in CR–ROM (8 pages), Osaka, Japan

  • Nakashima T, Takatani M, Ishibuchi H, Nii M (2006) The effect of using match history on the evolution of robocup soccer team strategies, Reno/Lake Tahoe, Nevada, USA, pp 60–66

  • Newborn M, Newborn M (1996) Kasparov versus deep blue: computer chess comes of age. Springer, New York

  • Nozaki K, Ishibuchi H, Tanaka H (1996) Adaptive fuzzy rule-based classification systems. IEEE Trans Fuzzy Syst 4:238–250

    Article  Google Scholar 

  • Quek H-Y, Goh CK (2007) Adaptation of iterated prisoner’s dilemma strategies by evolution and learning. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 40–47

  • Riedmiller M, Gabel T (2007) On experiences in a complex and competitive gaming domain: reinforcement learning meets robocup. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 17–23

  • Runarsson TP, Jonsson EO (2007) Effect of look-ahead search depth in learning position evaluation functions for othello using greedy exploration. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 210–215

  • Togelius J (2004) Evolution of a subsumption architecture neurocontroller. J Intell Fuzzy Syst 15:15–20

    Google Scholar 

  • Togelius J (2007) Optimization, lmitation and innovation: computational intelligence and games. PhD thesis, Department of Computer Science, University of Essex

  • Togelius J, Lucas SM (2006) Evolving robust and specialized car racing skills. In: Evolutionary computation, 2006. CEC 2006. IEEE Congress on, pp 1187–1194

  • Togelius J, Nardi RD, Lucas SM (2006) Making racing fun through player modeling and track evolution. In: SAB workshop on adaptive approaches to optimizing player satisfaction

  • Togelius J, Lucas SM, Nardi RD (2007a) Computational intelligence in racing games. Studies in computational intelligence, vol 71. Springer, Berlin, pp 39–69

  • Togelius J, De Nardi R, Lucas SM (2007b) Towards automatic personalised content creation for racing games. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 252–259

  • Vicenç Torra (2002) A review of the construction of hierarchical fuzzy systems. Int J Intell Syst 17(5):531–543

    Article  MATH  MathSciNet  Google Scholar 

  • Wang Y, Gelly S (2007) Modifications of uct and sequence-like simulations for monte-carlo go. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 175–182

  • Wittkamp M, Barone L, While L (2007) A comparison of genetic programming and look-up table learning for the game of spoof. In: Computational intelligence and games, 2007. CIG 2007. IEEE Symposium on, pp 63–71

Download references

Author information

Authors and Affiliations

  1. Graduate School of Engineering, Osaka Prefecture University, Gakuen-cho 1-1, Naka-ku, Sakai, Osaka, 599-8531, Japan

    Tomoharu Nakashima & Seiya Fujii

Authors
  1. Tomoharu Nakashima
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Seiya Fujii
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Tomoharu Nakashima.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Nakashima, T., Fujii, S. Designing high-level decision making systems based on fuzzy if–then rules for a point-to-point car racing game. Soft Comput 14, 517–528 (2010). https://doi.org/10.1007/s00500-009-0448-7

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-009-0448-7

Keywords

Search

Navigation