Discovering reoccurring motifs to predict opponent behavior

In contrast to human soccer players, autonomous robot soccer players often move according to a limited set of predefined behavioral rules. This knowledge can be used advantageously: If the opponent's behavioral rules are learned, it will be possible to detect these during a match and react accordingly. A method for autonomous activity mining in videos, called Probabilistic Latent Sequential Motifs, is used to discover optical flow patterns in videos of a robot soccer player during a penalty shootout. The discovered patterns are used by a humanoid goalkeeper to predict and anticipate opponent behavior. Effectiveness of the method is tested by comparing the performance of this goalkeeper with predictive behavior to that of an existing goalkeeper that only reacts when the ball approaches at sufficient speed. The performance is measured based on the ratio of number of goals to number of goals prevented. Results show that the goalkeeper with predictive behavior could prevent a fair amount of goals, but that it loses in performance to the existing goalkeeper. Methods that may improve performance are discussed.