A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 11 Issue 1
Jan.  2024

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 11.8, Top 4% (SCI Q1)
    CiteScore: 17.6, Top 3% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2024  >  11(1): 37-57
Z. Pu, Y. Pan, S. Wang, B. Liu, M. Chen, H. Ma, and Y. Cui, “Orientation and decision-making for soccer based on sports analytics and AI: A systematic review,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 37–57, Jan. 2024. doi: 10.1109/JAS.2023.123807
Citation: Z. Pu, Y. Pan, S. Wang, B. Liu, M. Chen, H. Ma, and Y. Cui, “Orientation and decision-making for soccer based on sports analytics and AI: A systematic review,” IEEE/CAA J. Autom. Sinica, vol. 11, no. 1, pp. 37–57, Jan. 2024. doi: 10.1109/JAS.2023.123807
shu

Orientation and Decision-Making for Soccer Based on Sports Analytics and AI: A Systematic Review

doi: 10.1109/JAS.2023.123807
Funds:  This work was supported by the National Key Research, Development Program of China (2020AAA0103404), the Beijing Nova Program (20220484077), and the National Natural Science Foundation of China (62073323)
More Information
    Abstract
  • Due to ever-growing soccer data collection approaches and progressing artificial intelligence (AI) methods, soccer analysis, evaluation, and decision-making have received increasing interest from not only the professional sports analytics realm but also the academic AI research community. AI brings game-changing approaches for soccer analytics where soccer has been a typical benchmark for AI research. The combination has been an emerging topic. In this paper, soccer match analytics are taken as a complete observation-orientation-decision-action (OODA) loop. In addition, as in AI frameworks such as that for reinforcement learning, interacting with a virtual environment enables an evolving model. Therefore, both soccer analytics in the real world and virtual domains are discussed. With the intersection of the OODA loop and the real-virtual domains, available soccer data, including event and tracking data, and diverse orientation and decision-making models for both real-world and virtual soccer matches are comprehensively reviewed. Finally, some promising directions in this interdisciplinary area are pointed out. It is claimed that paradigms for both professional sports analytics and AI research could be combined. Moreover, it is quite promising to bridge the gap between the real and virtual domains for soccer match analysis and decision-making.

     

    • FullText(HTML)
  • loading
    • References(154)
  • [1]
    F. R. Goes, L. A. Meerhoff, M. J. O. Bueno, D. M. Rodrigues, F. A. Moura, M. S. Brink, M. T. Elferink-Gemser, A. J. Knobbe, S. A. Cunha, R. S. Torres, and K. A. P. M. Lemmink, “Unlocking the potential of big data to support tactical performance analysis in professional soccer: A systematic review,” Eur. J. Sport Sci., vol. 21, no. 4, pp. 481–496, Apr. 2021. doi: 10.1080/17461391.2020.1747552
    [2]
    J. Davis, L. Bransen, L. Devos, W. Meert, P. Robberechts, J. Van Haaren, and M. Van Roy, “Evaluating sports analytics models: Challenges, approaches, and lessons learned,” in Proc. Workshop on AI Evaluation Beyond Metrics Co-Located with the 31st Int. Joint Conf. Artificial Intelligence, Vienna, Austria, 2022, pp. 1–11.
    [3]
    K. Tuyls, S. Omidshafiei, P. Muller, Z. Wang, J. Connor, D. Hennes, I. Graham, W. Spearman, T. Waskett, D. Steel, P. Luc, A. Recasens, A. Galashov, G. Thornton, R. Elie, P. Sprechmann, P. Moreno, K. Cao, M. Garnelo, P. Dutta, M. Valko, N. Heess, A. Bridgland, J. Pérolat, B. D. Vylder, S. M. A. Eslami, M. Rowland, A. Jaegle, R. Munos, T. Back, R. Ahamed, S. Bouton, N. Beauguerlange, J. Broshear, T. Graepel, and D. Hassabis, “Game plan: What AI can do for football, and what football can do for AI,” J. Artif. Intell. Res., vol. 71, pp. 41–88, May 2021. doi: 10.1613/jair.1.12505
    [4]
    K. Kurach, A. Raichuk, P. Stanczyk, M. Zajac, O. Bachem, L. Espeholt, C. Riquelme, D. Vincent, M. Michalski, O. Bousquet, and S. Gelly, “Google research football: A novel reinforcement learning environment,” in Proc. 34th AAAI Conf. Artificial Intelligence, The 32nd Innovative Applications of Artificial Intelligence Conf., The 10th AAAI Symp. Educational Advances in Artificial Intelligence, New York, USA, 2020, pp. 4501–4510.
    [5]
    J. Liu, X. Zhu, F. Liu, L. Guo, Z. Zhao, M. Sun, W. Wang, J. Wang, and H. Lu, “OPT: Omni-perception pre-trainer for cross-modal understanding and generation,” arXiv preprint arXiv: 2107.00249, 2021.
    [6]
    P. Wang, A. Yang, R. Men, J. Lin, S. Bai, Z. Li, J. Ma, C. Zhou, J. Zhou, and H. Yang, “OFA: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework,” in Proc. 39th Int. Conf. Machine Learning, Baltimore, USA, 2022, pp. 23318–23340.
    [7]
    A. Ramesh, M. Pavlov, G. Goh, S. Gray, C. Voss, A. Radford, M. Chen, and I. Sutskever, “Zero-shot text-to-image generation,” in Proc. 38th Int. Conf. Machine Learning, 2021, pp. 8821–8831.
    [8]
    X. Chen, X. Wang, S. Changpinyo, A. J. Piergiovanni, P. Padlewski, D. Salz, S. Goodman, A. Grycner, B. Mustafa, L. Beyer, A. Kolesnikov, J. Puigcerver, N. Ding, K. Rong, H. Akbari, G. Mishra, L. Xue, A. V. Thapliyal, J. Bradbury, and W. Kuo, “PaLI: A jointly-scaled multilingual language-image model,” in Proc. 11th Int. Conf. Learning Representations, Kigali, Rwanda, 2022.
    [9]
    D. Silver, A. Huang, C. J. Maddison, A. Guez, L. Sifre, G. Van Den driessche, J. Schrittwieser, I. Antonoglou, V. Panneershelvam, M. Lanctot, S. Dieleman, D. Grewe, J. Nham, N. Kalchbrenner, I. Sutskever, T. Lillicrap, M. Leach, K. Kavukcuoglu, T. Graepel, and D. Hassabis, “Mastering the game of Go with deep neural networks and tree search,” Nature, vol. 529, no. 7587, pp. 484–489, Jan. 2016. doi: 10.1038/nature16961
    [10]
    O. Vinyals, I. Babuschkin, W. M. Czarnecki, M. Mathieu, A. Dudzik, J. Chung, D. H. Choi, R. Powell, T. Ewalds, P. Georgiev, J. Oh, D. Horgan, M. Kroiss, I. Danihelka, A. Huang, L. Sifre, T. Cai, J. P. Agapiou, M. Jaderberg, A. S. Vezhnevets, R. Leblond, T. Pohlen, V. Dalibard, D. Budden, Y. Sulsky, J. Molloy, T. L. Paine, C. Gulcehre, Z. Y. Wang, T. Pfaff, Y. H. Wu, R. Ring, D. Yogatama, D. Wünsch, K. Mckinney, O. Smith, T. Schaul, T. Lillicrap, K. Kavukcuoglu, D. Hassabis, C. Apps, and D. Silver, “Grandmaster level in StarCraft II using multi-agent reinforcement learning,” Nature, vol. 575, no. 7782, pp. 350–354, Oct. 2019. doi: 10.1038/s41586-019-1724-z
    [11]
    A. Fawzi, M. Balog, A. Huang, T. Hubert, B. Romera-Paredes, M. Barekatain, A. Novikov, F. J. R. Ruiz, J. Schrittwieser, G. Swirszcz, D. Silver, D. Hassabis, and P. Kohli, “Discovering faster matrix multiplication algorithms with reinforcement learning,” Nature, vol. 610, no. 7930, pp. 47–53, Oct. 2022. doi: 10.1038/s41586-022-05172-4
    [12]
    C. Berner, G. Brockman, B. Chan, V. Cheung, P. Dębiak, C. Dennison, D. Farhi, Q. Fischer, S. Hashme, C. Hesse, R. Józefowicz, S. Gray, C. Olsson, J. Pachocki, M. Petrov, H. P. D. O. Pinto, J. Raiman, T. Salimans, J. Schlatter, J. Schneider, S. Sidor, I. Sutskever, J. Tang, F. Wolski, and S. Zhang, “Dota 2 with large scale deep reinforcement learning,” arXiv preprint arXiv: 1912.06680, 2019.
    [13]
    B. Baker, I. Kanitscheider, T. M. Markov, Y. Wu, G. Powell, B. McGrew, and I. Mordatch, “Emergent tool use from multi-agent autocurricula,” in Proc. 8th Int. Conf. Learning Representations, 2019.
    [14]
    M. Andrychowicz, B. Baker, M. Chociej, R. Józefowicz, B. McGrew, J. Pachocki, A. Petron, M. Plappert, G. Powell, A. Ray, J. Schneider, S. Sidor, J. Tobin, P. Welinder, L. Weng, and W. Zaremba, “Learning dexterous in-hand manipulation,” Int. J. Rob. Res., vol. 39, no. 1, pp. 3–20, Jan. 2020. doi: 10.1177/0278364919887447
    [15]
    H. Eggels, R. van Elk, and M. Pechenizkiy, “Explaining soccer match outcomes with goal scoring opportunities predictive analytics,” in Proc. 3rd Workshop on Machine Learning and Data Mining for Sports Analytics, Riva del Garda, Italy, 2016.
    [16]
    C. Biermann, Football Hackers: The Science and Art of A Data Revolution. Blink Publishing, 2019.
    [17]
    J. Tippett, The Expected Goals Philosophy: A Game-Changing Way of Analysing Football. Independently Published, 2019.
    [18]
    J. Fernández, L. Bornn, and D. Cervone, “Decomposing the immeasurable sport: A deep learning expected possession value framework for soccer,” in Proc. MIT Sloan Sports Analytics Conf., 2019.
    [19]
    J. Fernandez, F. Barcelona, and L. Bornn, “Wide open spaces: A statistical technique for measuring space creation in professional soccer,” in Proc. 12th Annu. MIT Sloan Sports Analytics Conf., 2018.
    [20]
    Y. Huang, “Modeling and simulation method of the emergency response systems based on OODA,” Knowl.-Based Syst., vol. 89, pp. 527–540, Nov. 2015. doi: 10.1016/j.knosys.2015.08.020
    [21]
    Y. Niu, R. Paleja, and M. Gombolay, “Multi-agent graph-attention communication and teaming,” in Proc. 20th Int. Conf. Autonomous Agents and MultiAgent Systems, 2021, pp. 964–973.
    [22]
    Z. Pu, H. Wang, B. Liu, and J. Yi, “Cognition-driven multiagent policy learning framework for promoting cooperation,” IEEE Trans. Games, vol. 15, p. 3, Sept. 2023. doi: 10.1109/TG.2023.3310831
    [23]
    Google. (2020). Google Research Football Competition. [Online]. Available: https://www.kaggle.com/c/google-football.
    [24]
    W. Zhao, J. P. Queralta, and T. Westerlund, “Sim-to-real transfer in deep reinforcement learning for robotics: A survey,” in Proc. IEEE Symp. Series on Computational Intelligence, Canberra, Australia, 2020, pp. 737–744.
    [25]
    T. Zhang, K. Zhang, J. Lin, W. Y. G. Louie, and H. Huang, “Sim2real learning of obstacle avoidance for robotic manipulators in uncertain environments,” IEEE Rob. Autom. Lett., vol. 7, no. 1, pp. 65–72, Jan. 2022. doi: 10.1109/LRA.2021.3116700
    [26]
    I. Palacios-Huerta, “Professionals play minimax,” Rev. Econ. Stud., vol. 70, no. 2, pp. 395–415, Apr. 2003. doi: 10.1111/1467-937X.00249
    [27]
    StatsBomb, “Free football data from StatsBomb,” [Online]. Available: https://github.com/statsbomb/open-data.
    [28]
    L. Pappalardo and E. Massucco, “Soccer match event dataset,” 2019. [Online]. Available: https://doi.org/10.6084/m9.figshare.c.4415000.v1.
    [29]
    H. Jiang, Y. Lu, and J. Xue, “Automatic soccer video event detection based on a deep neural network combined CNN and RNN,” in Proc. 28th Int. Conf. Tools with Artificial Intelligence, San Jose, USA, 2016, pp. 490–494.
    [30]
    H.-Y. Liu and T. He, “Integrating multiple feature fusion for semantic event detection in soccer video,” in Proc. Int. Joint Conf. Artificial Intelligence, Hainan, China, 2009, pp. 128–131.
    [31]
    J. Lee, D. W. Nam, S. Moon, J. S. Lee, and W. Yoo, “Soccer event recognition technique based on pattern matching,” in Proc. Federated Conf. Computer Science and Information Systems, Prague, Czech Republic, 2017, pp. 643–646.
    [32]
    SkillCorner. SkillCorner official website. [Online]. Available: https://www.skillcorner.com.
    [33]
    S. Spectrum. Second Spectrum official website. [Online]. Available: https://www.secondspectrum.com/index.html.
    [34]
    S. Perform. Stats Perform official website. [Online]. Available: https://www.statsperform.com.
    [35]
    Metrica. Metrica official website. [Online]. Available: https://metrica-sports.com.
    [36]
    Signality. Signality official website. [Online]. Available: https://www.signality.com.
    [37]
    SkillCorner, “SkillCorner open data,” 2020. [Online]. Available: https://github.com/SkillCorner/opendata.
    [38]
    Metrica, “Metrica Sports sample tracking and event data,” 2020. [Online]. Available: https://github.com/metrica-sports/sample-data.
    [39]
    M. Xu, J. Orwell, and G. Jones, “Tracking football players with multiple cameras,” in Proc. Int. Conf. Image Processing, Singapore, 2004, pp. 2909–2912.
    [40]
    R. Zhang, L. Wu, Y. Yang, W. Wu, Y. Chen, and M. Xu, “Multi-camera multi-player tracking with deep player identification in sports video,” Pattern Recognit., vol. 102, p. 107260, Jun. 2020. doi: 10.1016/j.patcog.2020.107260
    [41]
    M. Beetz, S. Gedikli, J. Bandouch, B. Kirchlechner, N. V. Hoyningen-Huene, and A. Perzylo, “Visually tracking football games based on TV broadcasts,” in Proc. 20th Int. Joint Conf. Artificial Intelligence, Hyderabad, India, 2007, pp. 2066–2071.
    [42]
    S. Omidshafiei, D. Hennes, M. Garnelo, Z. Wang, A. Recasens, E. Tarassov, Y. Yang, R. Elie, J. T. Connor, P. Muller, N. Mackraz, K. Cao, P. Moreno, P. Sprechmann, D. Hassabis, I. Graham, W. Spearman, N. Heess, and K. Tuyls, “Multiagent off-screen behavior prediction in football,” Sci. Rep., vol. 12, no. 1, p. 8638, May 2022. doi: 10.1038/s41598-022-12547-0
    [43]
    R. J. Aughey, “Applications of GPS technologies to field sports,” in Int. J. Sports Physiol. Perform., vol. 6, no. 3, pp. 295–310, Sep. 2011.
    [44]
    C. Cummins, R. Orr, H. O’Connor, and C. West, “Global positioning systems (GPS) and microtechnology sensors in team sports: A systematic review,” Sports Med., vol. 43, no. 10, pp. 1025–1042, Jun. 2013. doi: 10.1007/s40279-013-0069-2
    [45]
    R. Leser, A. Schleindlhuber, K. Lyons, and A. Baca, “Accuracy of an UWB-based position tracking system used for time-motion analyses in game sports,” Eur. J. Sport Sci., vol. 14, no. 7, pp. 635–642, Feb. 2014. doi: 10.1080/17461391.2014.884167
    [46]
    R. Tatman. The UMass Global English on Twitter Dataset. [Online]. Available: https://www.kaggle.com/datasets/rtatman/the-umass-global-english-on-twitter-dataset.
    [47]
    S. Yadav. (2017). Pre-Processed Twitter Tweets. [Online]. Available: https://www.kaggle.com/datasets/shashank1558/preprocessed-twitter-tweets.
    [48]
    L. Morra, F. Manigrasso, and F. Lamberti, “SoccER: Computer graphics meets sports analytics for soccer event recognition,” SoftwareX, vol. 12, p. 100612, Jul.–Dec. 2020. doi: 10.1016/j.softx.2020.100612
    [49]
    Google. (2020). Google Research Football Competition Data. [Online]. Available: https://www.kaggle.com/datasets/dott1718/grf-replays-collection.
    [50]
    O. Michael, O. Obst, F. Schmidsberger, and F. Stolzenburg, “RoboCupSimData: A RoboCup soccer research dataset,” arXiv preprint arXiv: 1711.01703, 2017.
    [51]
    S. Liu, G. Lever, Z. Wang, J. Merel, S. M. Ali Eslami, D. Hennes, W. M. Czarnecki, Y. Tassa, S. Omidshafiei, A. Abdolmaleki, N. Y. Siegel, L. Hasenclever, L. Marris, S. Tunyasuvunakool, H. Francis Song, M. Wulfmeier, P. Muller, T. Haarnoja, B. D. Tracey, K. Tuyls, T. Graepel, and N. Heess, “From motor control to team play in simulated humanoid football,” Science Robotics, vol. 7, no. 69, p. eabo0235, Aug. 2022. doi: 10.1126/scirobotics.abo0235
    [52]
    Y. Zeng, G. Shen, B. Chen, and J. Tang, “Team composition in PES2018 using submodular function optimization,” IEEE Access, vol. 7, pp. 76194–76202, May 2019. doi: 10.1109/ACCESS.2019.2919447
    [53]
    M. Prado Prandini Faria, R. Maria Silva Julia, and L. Bononi Paiva Tomaz, “Evaluating the performance of the deep active imitation learning algorithm in the dynamic environment of FIFA player agents,” in Proc. 18th Int. Conf. Machine Learning and Applications, Boca Raton, USA, 2019, pp. 228–233.
    [54]
    M. A. Al-Asadi and S. Tasdemır, “Predict the value of football players using FIFA video game data and machine learning techniques,” IEEE Access, vol. 10, pp. 22631–22645, Feb. 2022. doi: 10.1109/ACCESS.2022.3154767
    [55]
    T. Decroos, L. Bransen, J. Van Haaren, and J. Davis, “Actions speak louder than goals: Valuing player actions in soccer,” in Proc. 25th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, Anchorage, USA, 2019, pp. 1851–1861.
    [56]
    T. Decroos, L. Bransen, J. Van Haaren, and J. Davis, “VAEP: An objective approach to valuing on-the-ball actions in soccer (extended abstract),” in Proc. 29th Int. Joint Conf. Artificial Intelligence, Yokohama, Japan, 2020.
    [57]
    A. C. Sankaranarayanan, A. Veeraraghavan, and R. Chellappa, “Object detection, tracking and recognition for multiple smart cameras,” Proc. IEEE, vol. 96, no. 10, pp. 1606–1624, Oct. 2008. doi: 10.1109/JPROC.2008.928758
    [58]
    M. Kos and I. Kramberger, “A wearable device and system for movement and biometric data acquisition for sports applications,” IEEE Access, vol. 5, pp. 6411–6420, Mar. 2017.
    [59]
    H. M. S. Hossain, M. A. Al Hafiz Khan, and N. Roy, “SoccerMate: A personal soccer attribute profiler using wearables,” in Proc. IEEE Int. Conf. Pervasive Computing and Communications Workshops, Kona, USA, 2017, pp. 164–169.
    [60]
    R. Patel and K. Passi, “Sentiment analysis on twitter data of world cup soccer tournament using machine learning,” IoT, vol. 1, no. 2, pp. 218–239, Oct. 2020. doi: 10.3390/iot1020014
    [61]
    B. Vanderplaetse and S. Dupont, “Improved soccer action spotting using both audio and video streams,” in Proc. IEEE/CVF Conf. Computer Vision and Pattern Recognition Workshops, Seattle, USA, 2020.
    [62]
    O. Michael, O. Obst, F. Schmidsberger, and F. Stolzenburg, “RoboCupSimData: Software and data for machine learning from RoboCup simulation league,” in Proc. RoboCup 2018: Robot World Cup XXII, Montreal, Canada, pp. 230–237.
    [63]
    H. Mellmann, B. Schlotter, and P. Strobel, “Toward data driven development in RoboCup,” in Proc. RoboCup 2019: Robot World Cup XXIII, Sydney, Australia, pp. 176–188.
    [64]
    P. H. Abreu, J. Moura, D. C. Silva, L. P. Reis, and J. Garganta, “Performance analysis in soccer: A cartesian coordinates based approach using RoboCup data,” Soft Comput., vol. 16, no. 1, pp. 47–61, May 2012. doi: 10.1007/s00500-011-0733-0
    [65]
    S. O’Keeffe and R. Villing, “A benchmark data set and evaluation of deep learning architectures for ball detection in the RoboCup SPL,” in Proc. RoboCup 2017: Robot World Cup XXI, Nagoya, Japan, pp. 398–409.
    [66]
    A. Scott, K. Fujii, and M. Onishi, “How does AI play football? An analysis of RL and real-world football strategies,” in Proc. 14th Int. Conf. Agents and Artificial Intelligence, 2022.
    [67]
    Q. Wang, H. Zhu, W. Hu, Z. Shen, and Y. Yao, “Discerning tactical patterns for professional soccer teams: An enhanced topic model with applications,” in Proc. 21th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Sydney, Australia, 2015, pp. 2197–2206.
    [68]
    J. Fernandez-Navarro, L. Fradua, A. Zubillaga, P. R. Ford, and A. P. Mcrobert, “Attacking and defensive styles of play in soccer: Analysis of Spanish and English elite teams,” J. Sports Sci., vol. 34, no. 24, pp. 2195–2204, Apr. 2016. doi: 10.1080/02640414.2016.1169309
    [69]
    A. Rathke, “An examination of expected goals and shot efficiency in soccer,” J. Hum. Sport Exercise, vol. 12, no. Proc2, pp. S514–S529, 2017.
    [70]
    S. Chawla, J. Estephan, J. Gudmundsson, and M. Horton, “Classification of passes in football matches using spatiotemporal data,” ACM Trans. Spat. Algorithms Syst., vol. 3, no. 2, p. 6, Aug. 2017.
    [71]
    L. Bransen and J. Van Haaren, “Measuring football players’ on-the-ball contributions from passes during games,” in Proc. 5th Int. Workshop on Machine Learning and Data Mining for Sports Analytics, Dublin, Ireland, 2018, pp. 3–15.
    [72]
    T. Decroos, J. Van Haaren, and J. Davis, “Automatic discovery of tactics in spatio-temporal soccer match data,” in Proc. 24th ACM SIGKDD Int. Conf. Knowledge Discovery & Data Mining, London, UK, 2018, pp. 223–232.
    [73]
    L. Pappalardo, P. Cintia, P. Ferragina, E. Massucco, D. Pedreschi, and F. Giannotti, “PlayeRank: Data-driven performance evaluation and player ranking in soccer via a machine learning approach,” ACM Trans. Intell. Syst. Technol., vol. 10, no. 5, p. 59, Sept. 2019.
    [74]
    J. Bekkers and S. Dabadghao, “Flow motifs in soccer: What can passing behavior tell us?” J. Sports Anal., vol. 5, no. 4, pp. 299–311, Dec. 2019. doi: 10.3233/JSA-190290
    [75]
    G. Liu, Y. Luo, O. Schulte, and T. Kharrat, “Deep soccer analytics: Learning an action-value function for evaluating soccer players,” Data Min. Knowl. Disc., vol. 34, no. 5, pp. 1531–1559, Jul. 2020. doi: 10.1007/s10618-020-00705-9
    [76]
    P. Robberechts and J. Davis, “How data availability affects the ability to learn good xG models,” in Proc. 7th Int. Workshop on Machine Learning and Data Mining for Sports Analytics, Ghent, Belgium, 2020, pp. 17–27.
    [77]
    T. Decroos and J. Davis, “Player vectors: Characterizing soccer players’ playing style from match event streams,” in Proc. European Conf. Machine Learning and Knowledge Discovery in Databases, Würzburg, Germany, 2019, pp. 569–584.
    [78]
    J. Van Haaren, ““Why would I trust your numbers?” On the explainability of expected values in soccer,” arXiv preprint arXiv: 2105.13778, 2021.
    [79]
    C. Merhej, R. J. Beal, T. Matthews, and S. Ramchurn, “What happened next? Using deep learning to value defensive actions in football event-data,” in Proc. 27th ACM SIGKDD Conf. Knowledge Discovery & Data Mining, Singapore, 2021, pp. 3394–3403.
    [80]
    P. Lucey, A. Bialkowski, M. Monfort, P. Carr, and I. Matthews, “Quality vs quantity: Improved shot prediction in soccer using strategic features from spatiotemporal data,” in Proc. 8th Conf. MIT Sloan Sports Analytics Conf., Boston, USA, 2014.
    [81]
    P. Power, H. Ruiz, X. Wei, and P. Lucey, “Not all passes are created equal: Objectively measuring the risk and reward of passes in soccer from tracking data,” in Proc. 23rd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Halifax, Canada, 2017, pp. 1605–1613.
    [82]
    W. Spearman, “Beyond expected goals,” in Proc. MIT Sloan Sports Analytics Conf., Boston, USA, 2018, pp. 1–17.
    [83]
    F. R. Goes, M. Kempe, L. A. Meerhoff, and K. A. P. M. Lemmink, “Not every pass can be an assist: A data-driven model to measure pass effectiveness in professional soccer matches,” Big Data, vol. 7, no. 1, pp. 57–70, Mar. 2019. doi: 10.1089/big.2018.0067
    [84]
    T. Mimura and Y. Nakada, “Quantification of pass plays based on geometric features of formations in team sports,” in Proc. 10th Int. Symp. on Information and Communication Technology, Hanoi, Viet Nam, 2019, pp. 306–313.
    [85]
    J. Fernandez-Navarro, L. Fradua, A. Zubillaga, and A. P. McRobert, “Evaluating the effectiveness of styles of play in elite soccer,” in Int. J. Sports Sci. Coa., vol. 14, no. 4, pp. 514–527, Aug. 2019.
    [86]
    K. Toda, M. Teranishi, K. Kushiro, and K. Fujii, “Evaluation of soccer team defense based on prediction models of ball recovery and being attacked,” arXiv preprint arXiv: 2103.09627, 2021.
    [87]
    J. Fernández, L. Bornn, and D. Cervone, “A framework for the fine-grained evaluation of the instantaneous expected value of soccer possessions,” Mach. Learn., vol. 110, no. 6, pp. 1389–1427, May 2021. doi: 10.1007/s10994-021-05989-6
    [88]
    U. Dick, D. Link, and U. Brefeld, “Who can receive the pass? A computational model for quantifying availability in soccer,” Data Min. Knowl. Disc., vol. 36, no. 3, pp. 987–1014, Mar. 2022. doi: 10.1007/s10618-022-00827-2
    [89]
    M. Andrzejewski, J. Chmura, and B. Pluta, “Analysis of motor and technical activities of professional soccer players of the UEFA Europa league,” in Int. J. Perform. Anal. Sport, vol. 14, no. 2, pp. 504–523, Apr. 2014.
    [90]
    B. Gong, Y. Cui, S. Zhang, C. Zhou, Q. Yi, and M.-Á. Gómez-Ruano, “Impact of technical and physical key performance indicators on ball possession in the Chinese super league,” Int. J. Perform. Anal. Sport, vol. 21, no. 6, pp. 909–921, Jul. 2021. doi: 10.1080/24748668.2021.1957296
    [91]
    T. Taki and J. Hasegawa, “Visualization of dominant region in team games and its application to teamwork analysis,” in Proc. Int. Conf. Computer Graphics, Geneva, Switzerland, 2000, pp. 227–235.
    [92]
    S. Fonseca, J. Milho, B. Travassos, and D. Araújo, “Spatial dynamics of team sports exposed by Voronoi diagrams,” Hum. Mov. Sci., vol. 31, no. 6, pp. 1652–1659, Dec. 2012. doi: 10.1016/j.humov.2012.04.006
    [93]
    S. Fonseca, J. Milho, B. Travassos, D. Araújo, and A. Lopes, “Measuring spatial interaction behavior in team sports using superimposed Voronoi diagrams,” in Int. J. Perform. Anal. Sport, vol. 13, no. 1, pp. 179–189, Mar. 2013.
    [94]
    R. Nakanishi, J. Maeno, K. Murakami, and T. Naruse, “An approximate computation of the dominant region diagram for the real-time analysis of group behaviors,” in Proc. RoboCup 2009: Robot Soccer World Cup XIII, Graz, Austria, pp. 228–239.
    [95]
    A. Fujimura and K. Sugihara, “Geometric analysis and quantitative evaluation of sport teamwork,” Syst. Comput. Jpn., vol. 36, no. 6, pp. 49–58, Jun. 2005. doi: 10.1002/scj.20254
    [96]
    J. Gudmundsson and T. Wolle, “Football analysis using spatio-temporal tools,” in Proc. 20th Int. Conf. Advances in Geographic Information Systems, Redondo Beach, California, 2012, pp. 566–569.
    [97]
    W. Spearman, A. Basye, G. Dick, R. Hotovy, and P. Pop, “Physics-based modeling of pass probabilities in soccer,” in Proc. MIT Sloan Sports Analytics Conf., 2017.
    [98]
    M. Stöckl, T. Seidl, D. Marley, and P. Power, “Making offensive play predictable-using a graph convolutional network to understand defensive performance in soccer,” in Proc. MIT Sloan Sports Analytics Conf., 2021.
    [99]
    L. Bransen and J. Van Haaren, “Player chemistry: Striving for a perfectly balanced soccer team,” arXiv preprint arXiv: 2003.01712, 2020.
    [100]
    S. Green. (2012). Accessing the Performance of Premier League Goal Scores. [Online]. Available: https://www.statsperform.com/resource/assessing-the-performance-of-premier-league-goalscorers/.
    [101]
    Pinnacle. (2017). An Analysis of Different Expected Goals Models. [Online]. Available: https://www.pinnacle.com/en/betting-articles/Soccer/expected-goals-model-analysis/MEP2N9VMG5CTW99D, Accessed on: Nov. 10, 2017.
    [102]
    K. Singh. Introducing expected threat (xT). [Online]. Available: https://karun.in/blog/expected-threat.html.
    [103]
    M. Van Roy, P. Robberechts, T. Decroos, and J. Davis, “Valuing on-the-ball actions in soccer: A critical comparison of XT and VAEP,” in Proc. AAAI Workshop on Artificial Intelligence in Team Sports, 2020.
    [104]
    J. Whitmore. (2021). What are Expected Assists (xA)? [Online]. Available: https://theanalyst.com/eu/2021/03/what-are-expected-assists-xa/, Accessed on: Mar. 24, 2021.
    [105]
    A. Arroyo. (2021). Expected Assists (xA): What Is It and How It Works? [Online]. Available: https://www.driblab.com/analysis-player/expected-assists-xa-what-is-it-and-how-it-works/, Accessed on: Jun. 30, 2021.
    [106]
    T. Lawrence. (2018). Introducing xGChain and xGBuildup. [Online]. Available: https://statsbomb.com/articles/soccer/introducing-xgchain-and-xgbuildup/, Accessed on: Aug. 30, 2018.
    [107]
    Y. Li, R. Ma, B. Gonçalves, B. Gong, Y. Cui, and Y. Shen, “Data-driven team ranking and match performance analysis in Chinese football super league,” Chaos,Solitons Fractals, vol. 141, p. 110330, Dec. 2020. doi: 10.1016/j.chaos.2020.110330
    [108]
    A. Geerts and T. Decroos, “Characterizing soccer players’ playing style from match event streams,” in Proc. 5th Workshop on Machine Learning and Data Mining for Sports Analytics Co-Located with 2018 European Conf. Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Dublin, Ireland, pp. 115–126.
    [109]
    A. Bialkowski, P. Lucey, P. Carr, Y. Yue, S. Sridharan, and I. Matthews, “Identifying team style in soccer using formations learned from spatiotemporal tracking data,” in Proc. IEEE Int. Conf. Data Mining Workshop, Shenzhen, China, 2014, pp. 9–14.
    [110]
    S. Merckx, P. Robberechts, Y. Euvrard, and J. Davis, “Measuring the effectiveness of pressing in soccer,” in Proc. 8th Workshop on Machine Learning and Data Mining for Sports Analytics, 2021.
    [111]
    J. Mallo, E. Mena, F. Nevado, and V. Paredes, “Physical demands of top-class soccer friendly matches in relation to a playing position using global positioning system technology,” J. Hum. Kinet., vol. 47, no. 1, pp. 179–188, Sept. 2015. doi: 10.1515/hukin-2015-0073
    [112]
    T. Modric, S. Versic, D. Sekulic, and S. Liposek, “Analysis of the association between running performance and game performance indicators in professional soccer players,” in Int. J. Environ. Res. Public Health, vol. 16, no. 20, pp. 4032, Oct. 2019.
    [113]
    D. Castillo, J. Yanci, J. A. Casajús, and J. Cámara, “Physical fitness and physiological characteristics of soccer referees,” Sci. Sports, vol. 31, no. 1, pp. 27–35, Feb. 2016. doi: 10.1016/j.scispo.2015.11.003
    [114]
    D. Castillo, J. Cámara, D. Lozano, C. Berzosa, and J. Yanci, “The association between physical performance and match-play activities of field and assistants soccer referees,” Res. Sports Med., vol. 27, no. 3, pp. 283–297, Jul. 2019. doi: 10.1080/15438627.2018.1534117
    [115]
    D. Ye, Z. Liu, M. Sun, B. Shi, P. Zhao, H. Wu, H. Yu, S. Yang, X. Wu, Q. Guo, Q. Chen, Y. Yin, H. Zhang, T. Shi, L. Wang, Q. Fu, W. Yang, and L. Huang, “Mastering complex control in MOBA games with deep reinforcement learning,” in Proc. 34th AAAI Conf. Artificial Intelligence, The 32nd Innovative Applications of Artificial Intelligence Conf., The 10th AAAI Symp. Educational Advances in Artificial Intelligence, New York, USA, 2020, pp. 6672–6679.
    [116]
    RL Card Data Lab. RLCard: A toolkit for reinforcement learning in card games. [Online]. Available: https://rlcard.org/.
    [117]
    S. Ontañón, G. Synnaeve, A. Uriarte, F. Richoux, D. Churchill, and M. Preuss, “A survey of real-time strategy game AI research and competition in StarCraft,” IEEE Trans. Comput. Intell. AI Games, vol. 5, no. 4, pp. 293–311, Dec. 2013. doi: 10.1109/TCIAIG.2013.2286295
    [118]
    O. Vinyals, T. Ewalds, S. Bartunov, P. Georgiev, A. S. Vezhnevets, M. Yeo, A. Makhzani, H. Küttler, J. Agapiou, J. Schrittwieser, J. Quan, S. Gaffney, S. Petersen, K. Simonyan, T. Schaul, H. van Hasselt, D. Silver, T. Lillicrap, K. Calderone, P. Keet, A. Brunasso, D. Lawrence, A. Ekermo, J. Repp, and R. Tsing, “StarCraft II: A new challenge for reinforcement learning,” arXiv preprint arXiv: 1708.04782, 2017.
    [119]
    J. Brooks, M. Kerr, and J. V. Guttag, “Developing a data-driven player ranking in soccer using predictive model weights,” in Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, San Francisco, USA, 2016.
    [120]
    J. Fernández and L. Bornn, “SoccerMap: A deep learning architecture for visually-interpretable analysis in soccer,” in Proc. European Conf. Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track, Ghent, Belgium, 2020, pp. 491–506.
    [121]
    P. Garnier and T. Gregoir, “Evaluating soccer player: From live camera to deep reinforcement learning,” arXiv preprint arXiv: 2101.05388, 2021.
    [122]
    H. M. Le, P. Carr, Y. Yue, and P. Lucey, “Data-driven ghosting using deep imitation learning,” in Proc. MIT Sloan Sports Analytics Conf., 2017.
    [123]
    P. Rahimian, J. VanHaaren, T. Abzhanova, and L. Toka, “Beyond action valuation: A deep reinforcement learning framework for optimizing player decisions in soccer,” in Proc. MIT Sloan Sports Analytics Conf., 2022.
    [124]
    J. Perl, A. Grunz, and D. Memmert, “Tactics analysis in soccer–An advanced approach,” Int. J. Comput. Sci. Sport, vol. 12, no. 1, pp. 33–44, Jan. 2013.
    [125]
    A. Bialkowski, P. Lucey, P. Carr, Y. Yue, S. Sridharan, and I. Matthews, “Large-scale analysis of soccer matches using spatiotemporal tracking data,” in Proc. IEEE Int. Conf. Data Mining, Shenzhen, China, 2014, pp. 725–730.
    [126]
    A. Bialkowski, P. Lucey, P. Carr, Y. Yue, and I. Matthews, “Win at home and draw away: Automatic formation analysis highlighting the differences in home and away team behaviors,” in Proc. MIT Sloan Sports Analytics Conf., 2014, pp. 1–7.
    [127]
    Y. Wu, X. Xie, J. Wang, D. Deng, H. Liang, H. Zhang, S. Cheng, and W. Chen, “ForVizor: Visualizing spatio-temporal team formations in soccer,” IEEE Trans. Vis. Comput. Graph., vol. 25, no. 1, pp. 65–75, Aug. 2018.
    [128]
    H. Kim, B. Kim, D. Chung, J. Yoo, and S.-K. Ko, “SoccerCPD: Formation and role change-point detection in soccer matches using spatiotemporal tracking data,” in Proc. 28th ACM SIGKDD Conf. Knowledge Discovery and Data Mining, Washington, USA, 2022, pp. 3146–3156.
    [129]
    H. Mao, W. Liu, J. Hao, J. Luo, D. Li, Z. Zhang, J. Wang, and Z. Xiao, “Neighborhood cognition consistent multi-agent reinforcement learning,” in Proc. 34th AAAI Conf. Artificial Intelligence, The 32nd Innovative Applications of Artificial Intelligence Conf., The 10th AAAI Symp. Educational Advances in Artificial Intelligence, New York, USA, 2020, pp. 7219–7226.
    [130]
    J. Ruan, Y. Du, X. Xiong, D. Xing, X. Li, L. Meng, H. Zhang, J. Wang, and B. Xu, “GCS: Graph-based coordination strategy for multi-agent reinforcement learning,” in Proc. 21st Int. Conf. Autonomous Agents and Multiagent Systems, Auckland, New Zealand, 2022.
    [131]
    D. Yang and Y. Tang, “Adaptive inner-reward shaping in sparse reward games,” in Proc. Int. Joint Conf. Neural Networks, Glasgow, UK, 2020, pp. 1–8.
    [132]
    Z. Ma, R. Wang, L. Fei-Fei, M. S. Bernstein, and R. Krishna, “ELIGN: Expectation alignment as a multi-agent intrinsic reward,” in Proc. 36th Int. Conf. Neural Information Processing Systems, New Orleans, USA, 2022.
    [133]
    S. Li, X. Wang, W. Zhang, and X. Zhang, “A model-based approach to solve the sparse reward problem,” in Proc. 4th Int. Conf. Pattern Recognition and Artificial Intelligence, Yibin, China. 2021, pp. 476–480.
    [134]
    L. Wang, Y. Zhang, Y. Hu, W. Wang, C. Zhang, Y. Gao, J. Hao, T. Lv, and C. Fan, “Individual reward assisted multi-agent reinforcement learning,” in Proc. 39th Int. Conf. Machine Learning, Baltimore, USA, 2022, pp. 23417–23432.
    [135]
    T. Wang, T. Gupta, A. Mahajan, B. Peng, S. Whiteson, and C. Zhang, “RODE: Learning roles to decompose multi-agent tasks,” in Proc. 9th Int. Conf. Learning Representations, 2021.
    [136]
    C. Li, T. Wang, C. Wu, Q. Zhao, J. Yang, and C. Zhang, “Celebrating diversity in shared multi-agent reinforcement learning,”in Proc. 35th Conf. Neural Information Processing Systems, 2021, pp. 3991–4002.
    [137]
    Z. Xu, B. Zhang, D. Li, Z. Zhang, G. Zhou, H. Chen, and G. Fan, “Consensus learning for cooperative multi-agent reinforcement learning,” in Proc. 37th AAAI Conf. Artificial Intelligence and 35th Conf. Innovative Applications of Artificial Intelligence and 13th Symp. Educational Advances in Artificial Intelligence, Washington, USA, 2023.
    [138]
    T. Kharrat, I. G. McHale, and J. L. Peña, “Plus-minus player ratings for soccer,” Eur. J. Oper. Res., vol. 283, no. 2, pp. 726–736, Jun. 2020. doi: 10.1016/j.ejor.2019.11.026
    [139]
    A. Ali, “Measuring soccer skill performance: A review,” Scand. J. Med. Sci. Sports, vol. 21, no. 2, pp. 170–183, Apr. 2011. doi: 10.1111/j.1600-0838.2010.01256.x
    [140]
    M. Van Roy, P. Robberechts, W.-C. Yang, L. De Raedt, and J. Davis, “Leaving goals on the pitch: Evaluating decision making in soccer,” arXiv preprint arXiv: 2104.03252, 2021.
    [141]
    J. Gudmundsson and M. Horton, “Spatio-temporal analysis of team sports,” ACM Comput. Surv., vol. 50, no. 2, p. 22, Apr. 2017.
    [142]
    X. Wei, L. Sha, P. Lucey, S. Morgan, and S. Sridharan, “Large-scale analysis of formations in soccer,” in Proc. Int. Conf. Digital Image Computing: Techniques and Applications, Hobart, Australia, 2013, pp. 1–8.
    [143]
    J. Perl and D. Memmert, “Net-based game analysis by means of the software tool SOCCER,” Int. J. Comput. Sci. Sport, vol. 10, no. 2, pp. 77–84, Jan. 2011.
    [144]
    A. Grunz, D. Memmert, and J. Perl, “Tactical pattern recognition in soccer games by means of special self-organizing maps,” Hum. Mov. Sci., vol. 31, no. 2, pp. 334–343, Apr. 2012. doi: 10.1016/j.humov.2011.02.008
    [145]
    J. Perl and D. Memmert, “Soccer analyses by means of artificial neural networks, automatic pass recognition and Voronoi-cells: An approach of measuring tactical success,” in Proc. 10th Int. Symp. Computer Science in Sports, 2016, pp. 77–84.
    [146]
    P. Stone and M. Veloso, “Task decomposition, dynamic role assignment, and low-bandwidth communication for real-time strategic teamwork,” Artif. Intell., vol. 110, no. 2, pp. 241–273, Jun. 1999. doi: 10.1016/S0004-3702(99)00025-9
    [147]
    M. Tambe, J. Adibi, Y. Al-Onaizan, A. Erdem, G. A. Kaminka, S. C. Marsella, and I. Muslea, “Building agent teams using an explicit teamwork model and learning,” Artif. Intell., vol. 110, no. 2, pp. 215–239, Jun. 1999. doi: 10.1016/S0004-3702(99)00022-3
    [148]
    R. Lowe, J. Foerster, Y.-L. Boureau, J. Pineau, and Y. Dauphin, “On the pitfalls of measuring emergent communication,” in Proc. 18th Int. Conf. Autonomous Agents and MultiAgent Systems, Montreal, Canada, 2019.
    [149]
    M. Chen, Z. Pu, Y. Pan, and J. Yi, “Knowledge transfer from situation evaluation to multi-agent reinforcement learning,” in Proc. 29th Int. Conf. Neural Information Processing, 2022.
    [150]
    D. Yang, W. Yang, M. Li, and Q. Yang, “Role-based attention in deep reinforcement learning for games,” Comput. Anim. Virtual Worlds, vol. 32, no. 2, p. e1978, Apr. 2021. doi: 10.1002/cav.1978
    [151]
    B. Liu, Z. Pu, T. Zhang, H. Wang, J. Yi, and J. Mi, “Learning to play football from sports domain perspective: A knowledge-embedded deep reinforcement learning framework,” IEEE Trans. Games, 2022. DOI: 10.1109/TG.2022.3207068
    [152]
    H. He, J. Boyd-Graber, K. Kwok, and H. Daumé III, “Opponent modeling in deep reinforcement learning,” in Proc. 33rd Int. Conf. Machine Learning, New York, USA, 2016, pp. 1804–1813.
    [153]
    X. Liu, H. Jia, Y. Wen, Y. Hu, Y. Chen, C. Fan, Z. Hu, and Y. Yang, “Towards unifying behavioral and response diversity for open-ended learning in zero-sum games,”in Proc. 35th Conf. Neural Information Processing Systems, 2021, pp. 941–952.
    [154]
    R. Kirk, A. Zhang, E. Grefenstette, and T. Rocktäschel, “A survey of Zero-shot generalisation in deep reinforcement learning,” J. Artif. Intell. Res., vol. 76, pp. 201–264, Jan. 2023. doi: 10.1613/jair.1.14174
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(4)  / Tables(4)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (923) PDF downloads(216) Cited by()

    Highlights

    • We conduct a comprehensive literature review of soccer analysis, evaluation, and decision-making from an interdisciplinary perspective combing professional sports analytics and AI research. While these two separate areas have independently gained lots of success, their inherent paradigms are different. We attempt to point out some promising directions to combine these paradigms
    • An observation-orientation-decision-action (OODA) loop concept is adopted to characterize soccer match analysis, evaluation, and decision support process. Specifically, methods and algorithms for orientation and decision making are systematically addressed. This taxonomy helps better understand the inherent connections of different research and build up a roadmap for the overall research framework
    • Both real-world and virtual soccer matches in data supports, algorithms, and applications are discussed. Here the virtual domain indicates the flourishing AI paradigm where policy of an intelligent agent is evolved by interacting with an elaborately designed virtual environment. It opens a vast opportunity for convenient soccer match analysis. We claim that it is quite promising to bridge the gap between real and virtual matches
    • Some important issues that may be promising research directions for both professional soccer analytics and AI communities are pointed out. These issues include taking soccer as a benchmark for AI research, sim2real transfer, handling human-oriented factors, and unlocking more scenarios with the interdisciplinary tools

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return