Game-Watching Should be More Entertaining: Real-Time Application of Field-Situation Prediction to a Soccer Monitor

摘要

This paper describes an extension to a soccer monitor used in the RoboCup Soccer Simulation 2D League. The aim of the extension is to make the experience of watching games more entertaining. The audio effects and the visualization are focused on this purpose. The extended soccer monitor simulates the supporters' excitement in watching a game by estimating the time cycle until the next goal, which is called SituationScore. This paper describes how Situations core is obtained using a machine learning model and also describes the resulting soccer monitor. 1. github: https://github.com/rinmunagi/spectator_app 2. YouTube demo: https://youtu.be/J_NgcwcFtQI