AI Soccer: the Most Effective Methods to Dispossess the Opponent Player
S.A. Heslenfeld (TU Delft - Electrical Engineering, Mathematics and Computer Science)
Rafael Bidarra – Mentor (TU Delft - Computer Graphics and Visualisation)
K. Prakash – Mentor (TU Delft - Electrical Engineering, Mathematics and Computer Science)
S. Picek – Coach (TU Delft - Cyber Security)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
In this paper, one of the challenges that comes with defending in AI soccer is highlighted and an attempt is made in finding a solution for the problem. In soccer, defense is an important part of the game and the research question in this research is formulated as follows: what are the most effective methods to take by surprise and dispossess the attacking opponent player who carries the ball? To find the most optimal solutions for this problem, the Webots AI Soccer environment is used, which simulates a game of five versus five soccer. To be able to answer the research question, several approaches and strategies are implemented in the environment and their success is compared. This has led to the conclusion that, in this particular environment, defensive actions like slide tackling cannot be performed and thus cannot be used to defend. Therefore, other solutions are necessary, as a result, a combination of approaches is the most important way of making the dispossession strategy as successful as possible. This combination consists of predicting where the opponent is moving to with the ball and determining the optimal side to approach the opponent from.