Computational system for strategy design and match simulation in team sports

Abstract

The goal of the present work was to create a computational system that supports the design of strategies and the match simulation based on those strategies. A formal model of team strategy and match dynamics supported the specification of the computational system. In this model, team strategy was defined as a discrete dynamic system. The specification of individual action rules enables the team players to organize the collective action in every state of the system. A play is modelled by a sequence of compatible pairs of states. The system implementation encompasses a designing tool, whose resultant strategies are used as the input in a simulator capable of recognizing match states and applying the defined strategy to plan actions. Besides the inherent contribution to the investigation of team sports performance features, the presented framework may be helpful in other scientific areas, such as those that investigate cooperative actions in competitive environments and to the design of video-games with a greater realism, approximating them to real match simulators.