生成對抗網路應用於籃球防守戰術生成

Basketball Defensive Strategies Generation by Generative Adversarial Network

陳傑宇(Chieh-Yu Chen)

指導教授 ： 王昱舜

國立交通大學/資訊學院/多媒體工程研究所/碩士(2018年)

摘要

In this paper, we present a method to generate realistic defensive plays in a basketball game based on the ball and the offensive team’s movements. Our system allows players and coaches to simulate how the opposing team will react to a newly developed offensive strategy for evaluating its effectiveness. To achieve the aim, we train on the NBA dataset a conditional generative adversarial network that learns spatiotemporal interactions between players’ movements. The network consists of two components: a generator that takes a latent noise vector and the offensive team’s trajectories as input to generate defensive team’s trajectories; and a discriminator that evaluates the realistic degree of the generated results. Since a basketball game can be easily identified as fake if the ball handler, who is not defended, does not shoot the ball or cut into the restricted area, we add the wide open penalty to the objective function to assist model training. To evaluate the results, we compared the similarity of the real and the generated defensive plays, in terms of the players’ movement speed and acceleration, distance to defend ball handlers and non-ball handlers, and the frequency of wide open occurrences. In addition, we conducted a user study with 59 participants for subjective tests. Experimental results show the high fidelity of the generated defensive plays to real data and demonstrate the feasibility of our algorithm.

關鍵字

條件生成對抗網路 ； 籃球戰術 ； 模仿學習

並列摘要

In this paper, we present a method to generate realistic defensive plays in a basketball game based on the ball and the offensive team’s movements. Our system allows players and coaches to simulate how the opposing team will react to a newly developed offensive strategy for evaluating its effectiveness. To achieve the aim, we train on the NBA dataset a conditional generative adversarial network that learns spatiotemporal interactions between players’ movements. The network consists of two components: a generator that takes a latent noise vector and the offensive team’s trajectories as input to generate defensive team’s trajectories; and a discriminator that evaluates the realistic degree of the generated results. Since a basketball game can be easily identified as fake if the ball handler, who is not defended, does not shoot the ball or cut into the restricted area, we add the wide open penalty to the objective function to assist model training. To evaluate the results, we compared the similarity of the real and the generated defensive plays, in terms of the players’ movement speed and acceleration, distance to defend ball handlers and non-ball handlers, and the frequency of wide open occurrences. In addition, we conducted a user study with 59 participants for subjective tests. Experimental results show the high fidelity of the generated defensive plays to real data and demonstrate the feasibility of our algorithm.

並列關鍵字

Conditional Generative Adversarial Network ； Basketball Strategies ； Imitation Learning

參考文獻

[1] Arjovsky, M., & Bottou, L. (2017). Towards principled methods for training generative adversarial networks. stat 1050 (2017), 17.

[2] Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein gan. arXiv preprint arXiv:1701.07875 (2017).

[3] Ba, J. L., Kiros, J. R., & Hinton, G. E. (2016). Layer normalization. stat 1050 (2016), 21.

[4] Chen, C.-H., Liu, T.-L., Wang, Y.-S., Chu, H.-K., Tang, N. C., & Liao, H.-Y. M. (2015). Spatio-Temporal Learning of Basketball Offensive Strategies. In Proceedings of ACM international conference on Multimedia, (pp. 1123–1126).

[5] Franks, A., Miller, A., Bornn, L., & Goldsberry, K. (2015). Coun- terpoints: Advanced defensive metrics for nba basketball. In Proc. of MIT Sloan Sports Analytics Conference.