Skip to main content
SpringerLink
Log in

An automatic approach to extract goal plans from soccer simulated matches

  • Methodologies and Application
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Soccer is a competitive and collective sport in which teammates try to combine the execution of basic actions (cooperative behavior) to lead their team to more advantageous situations. The ability to recognize, extract and reproduce such behaviors can prove useful to improve the performance of a team in future matches. This work describes a methodology for achieving just that makes use of a plan definition language to abstract the representation of relevant behaviors in order to promote their reuse. Experiments were conducted based on a set of game log files generated by the Soccer Server simulator which supports the RoboCup 2D simulated robotic soccer league. The effectiveness of the proposed approach was verified by focusing primarily on the analysis of behaviors which started from set-pieces and led to the scoring of goals while the ball possession was kept. One of the results obtained showed that a significant part of the total goals scored was based on this type of behaviors, demonstrating the potential of conducting this analysis. Other results allowed us to assess the complexity of these behaviors and infer meaningful guidelines to consider when defining plans from scratch. Some possible extensions to this work include assessing which plans have the ability to maximize the creation of goal opportunities by countering the opponent’s team strategy and how the effectiveness of plans can be improved using optimization techniques.

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

Similar content being viewed by others

Notes

  1. Game situation in which the ball is returned to open play after a stoppage due to the ball going out-of-bounds or a call made by the referee. In a soccer match this includes kick-offs, goal-kicks, throw-ins, corner-kicks and free-kicks. In this work, the latter is also used to refer to indirect free-kicks.

  2. More information available online at http://sourceforge.net/projects/sserver/.

  3. More information available online at http://ne.cs.uec.ac.jp/*koji/SoccerScope2/index.htm.

  4. This cooperative behavior was exhibited by the WrightEagle team in the RoboCup 2010 quarter finals game against opuCI_2D at cycle 4551 and lasted 27 cycles.

References

  • Abreu PH, Faria M, Reis LP, Garganta J (2010a) Knowledge representation in soccer domain: an ontology development. In: Proceedings of the 2010 Iberian conference on information systems and technologies, pp 1–6

  • Abreu PH, Moura J, Silva DC, Reis LP, Garganta J (2010b) Football Scientia—an automated tool for professional soccer coaches. In: Proceedings of the 2010 IEEE international conference on cybernetics and intelligent systems (CIS 2010), June 28–30, 2010, Singapore. IEEE, pp 126–131

  • Abreu PH, Vinhas V, Mendes P, Reis LP, Garganta J (2010c) Real-time wireless location and tracking system with motion pattern detection. InTech, Robot localization and map building, pp 467–492

  • Abreu PH, Moura J, Silva DC, Reis LP, Garganta J (2011) Performance analysis in soccer: a Cartesian coordinates based approach using RoboCup data. In: Soft computing—a fusion of foundations, methodologies and applications, pp 1–15

  • Abreu PH, Mendes-Moreira J, Costa I, Castelão D, Reis LP, Garganta J (2012) Human versus virtual robotics soccer: a technical analysis. Eur J Sport Sci 12(1):26–35

    Article  Google Scholar 

  • Aler R, Valls JM, Camacho D, Lopez A (2009) Programming Robosoccer agents by modeling human behavior. Expert Syst Appl 36(2, Part 1):1850–1859

    Google Scholar 

  • Bauckhage C, Thurau C, Sagerer G (2003) Learning human-like opponent behavior for interactive computer games. In: DAGM symposium for pattern recognition, pp 148–155

  • Carling C, Williams A, Reilly T (2007) Handbook of soccer match analysis: a systematic approach to improving performance, 2nd edn. Routledge

  • de Dios Bulos R, Dulalia C, Go P, Tan P, Uy M (2005) A data mining approach in opponent modeling. In: Zhang S, Jarvis R (eds) AI 2005: advances in artificial intelligence. LNCS, vol 3809. Springer, Berlin, pp 993–996

  • Druecker C, Huebner S, Neumann H, Schmidt E, Visser U, Weland H (2000) Virtualweder: using the online-coach to change team formations. Technical report, University of Bremen

  • Fathzadeh R, Mokhtari V, Mousakhani M, Mahmoudi F (2006) Mining Opponent behavior: a champion of RoboCup coach competition. In: Robotics symposium, 2006. LARS ’06. IEEE 3rd Latin American, pp 80–83

  • Fathzadeh R, Mokhtari V, Kangavari MR (2008) Opponent provocation and behavior classification: a machine learning approach. In: RoboCup 2007: Robot Soccer World Cup XI. Springer, Berlin, pp 540–547

  • Gonzalez I, Abreu PH, Reis LP (2008) Using a datawarehouse to extract knowledge from robocup teams. In: Proceedings of the 2008 international conference on enterprise and information systems, pp 511–514

  • Iglesias JA, Fernández JA, Villena IR, Ledezma A, Sanchis A (2009a) The winning advantage: using opponent models in robot soccer. In: Proceedings of the 10th international conference on intelligent data engineering and automated learning, IDEAL’09. Springer, Berlin, pp 485–493

  • Iglesias JA, Ledezma A, Sanchis A (2009) CAOS Coach 2006 simulation team: an opponent modelling approach. Comput Inf 28(1):57–80

    Google Scholar 

  • Kok JR, Spaan MTJ, Vlassis N (2002) An approach to noncommunicative multiagent coordination in continuous domains. In: Wiering M (ed) Proceedings of the 12th Belgian-Dutch conference on machine learning, Utrecht, The Netherlands, pp 46–52

  • Kok JR, Spaan MTJ, Vlassis N (2003) Multi-robot decision making using coordination graphs. In: de Almeida AT, Nunes U (eds) Proceedings of the 11th international conference on advanced robotics, Coimbra, Portugal, pp 1124–1129

  • Kontes G, Lagoudakis M (2007) Coordinated team play in the four-legged RoboCup league. In: Proceedings of the 19th IEEE conference on tools with artificial intelligence (ICTAI), vol 1. IEEE Computer Society, Washington, pp 109–116

  • Kuhlmann G, Stone P, Lallinger J (2005) The UT Austin Villa 2003 champion simulator coach: a machine learning approach. In: Nardi D, Riedmiller M, Sammut C, Santos-Victor J (eds) RoboCup 2004: Robot Soccer World Cup VIII. LNCS, vol 3276. Springer, Berlin, pp 636–644

  • Ledezma A, Aler R, Sanchis A, Borrajo D (2005) Predicting opponent actions by observation. In: Nardi D, Riedmiller M, Sammut C, Santos-Victor J (eds) RoboCup 2004: Robot Soccer World Cup VIII, The RoboCup Federation. LNCS, vol 3276. Springer, Lisbon, pp 286–296

  • Ledezma A, Aler R, Sanchis A, Borrajo D (2009) OMBO: an opponent modeling approach. AI Community 22(1):21–35

    MathSciNet  MATH  Google Scholar 

  • Mota L, Lau N, Reis LP (2010) Co-ordination in RoboCup’s 2D simulation league: setplays as flexible, multi-robot plans. In: 2010 IEEE Conference on robotics automation and mechatronics (RAM), pp 362 –367

  • Noda I, Matsubara H, Hiraki K, Frank I (1998) Soccer server: a tool for research on multiagent systems. Appl Artif Intell 12(2–3):233–250

    Article  Google Scholar 

  • Obst O (2006) Using a planner for coordination of multiagent team behavior. In: Bordini RH, Dastani M, Dix JCBr, Seghrouchni AE (eds) Programming multi-agent systems: 3rd international workshop, ProMAS 2005, revised and invited papers, vol 3862. Springer, Berlin, pp 90–100

  • Obst O, Boedecker J (2006) Flexible coordination of multiagent team behavior using HTN planning. In: Noda I, Jacoff A, Bredenfeld A, Takahashi Y (eds) RoboCup 2005: Robot Soccer World Cup IX. Springer, Berlin, pp 521–528

  • Palamara PF, Ziparo VA, Iocchi L, Nardi D, Lima P (2009) Teamwork design based on Petri Net plans. In: Iocchi L, Matsubara H, Weitzenfeld A, Zhou C (eds) RoboCup 2008: Robot Soccer World Cup Xii, vol 5399. Springer, Berlin, pp 200–211

  • Portela J, Abreu PH, Reis LP, Oliveira EC, Garganta J (2010) An intelligent framework for automatic event detection in robotic soccer games: an auxiliar tool to help coaches improve their teams performance. In: Proceedings of the 2010 international conference on enterprise information systems, pp 244–249

  • Rad AA, Qaragozlou N, Zaheri M (2004) Scenario-based teamworking, how to learn, create, and teach complex plans? In: Polani D, Browning B, Bonarini A, Yoshida K (eds) RoboCup 2003: Robot Soccer World Cup VII, vol 3020. Springer, Berlin, pp 137–144

  • Riley P, Veloso M (2001) Coaching a simulated soccer team by opponent model recognition. In: Proceedings of the 5th international conference on autonomous agents, AGENTS ’01. ACM, New York, pp 155–156

  • Riley P, Veloso M (2006) Coach planning with opponent models for distributed execution. Auton Agent Multi-Agent Syst 13:293–325

    Article  Google Scholar 

  • Riley P, Veloso M, Kaminka G (2002) Towards any-team coaching in adversarial domains. In: Proceedings of the first international joint conference on autonomous agents and multiagent systems: part 3, AAMAS ’02. ACM, New York, pp 1145–1146

  • Steffens T (2004a) Adapting similarity-measures to agent-types in opponent-modelling. In: Bauer M, Gmytrasiewicz P, Kaminka GA, Pynadath DV (eds) Workshop on modeling other agents from observations at AAMAS, pp 125–128

  • Steffens T (2004b) Feature-based declarative opponent-modelling. In: Polani D, Browning B, Bonarini A, Yoshida K (eds) RoboCup 2003: Robot Soccer World Cup VII. LNCS, vol 3020. Springer, Berlin, pp 125–136

  • Steffens T (2005) Knowledge-intensive similarity-based opponent modelling. In: Aha DW (ed) Proceedings of the IJCAI workshop on representation, reasoning, and learning in computer games

  • Stone P, Riley P, Veloso M (2000) Defining and using ideal teammate and opponent agent models. In: Proceedings of the seventeenth national conference on artificial intelligence and twelfth conference on innovative applications of artificial intelligence. AAAI, San Francisco, pp 1040–1045

  • Ziparo VA, Iocchi L, Nardi D, Palamara PF, Costelha H (2008) Petri net plans: a formal model for representation and execution of multi-robot plans. In: Proceedings of the 7th international joint conference on international foundation for autonomous agents and multiagent systems, AAMAS’08, Richland, vol 1, pp 79–86

Download references

Acknowledgments

The first author was financially supported by a PROFAD scholarship from the Polytechnic Institute of Viseu.

Author information

Authors and Affiliations

  1. DI, Superior School of Technology of Viseu, Campus Politécnico de Repeses, 3504-510, Viseu, Portugal

    Fernando Almeida

  2. IEETA, Campus de Santiago, 3810-193, Aveiro, Portugal

    Fernando Almeida

  3. LIACC, Artificial Intelligence and Computer Science Laboratory, University of Porto, Rua Dr. Roberto Frias s/n, 4200-465, Porto, Portugal

    Fernando Almeida & Luís Paulo Reis

  4. DEI, CISUC, Faculty of Sciences and Technology, Rua Sílvio Lima, University of Coimbra, Pólo II, 3030-790, Coimbra, Portugal

    Pedro Henriques Abreu

  5. DETI, IEETA, University of Aveiro, Campus de Santiago, 3810-193, Aveiro, Portugal

    Nuno Lau

  6. EEUM, School of Engineering, University of Minho, DSI, Portugal Campus de Azurm, 4800-058, Guimarães, Portugal

    Luís Paulo Reis

Authors
  1. Fernando Almeida
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pedro Henriques Abreu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Nuno Lau
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Luís Paulo Reis
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Pedro Henriques Abreu.

Additional information

Communicated by E. Huellermeier.

Appendix: Set-play definition of a corner-kick with four participants

Appendix: Set-play definition of a corner-kick with four participants

figure f

Rights and permissions

Reprints and permissions

About this article

Cite this article

Almeida, F., Abreu, P.H., Lau, N. et al. An automatic approach to extract goal plans from soccer simulated matches. Soft Comput 17, 835–848 (2013). https://doi.org/10.1007/s00500-012-0952-z

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-012-0952-z

Keywords

Search

Navigation