Strategy planner: graphical definition of soccer set-plays

Abstract

One of the research topics on multi-agent systems focuses on the development of mechanisms such as plans to empower a team of agents to cooperate in order to perform complex tasks. In many cases, the definition of these plans are based on a specific and rather complex grammar and stored in structured text files. In the context of the 2D simulated Robotic Soccer domain, a set-play language was proposed to coordinate the execution of teammates' behaviors to improve a team's overall performance. The process of manually writing set-play definitions is hazardous and can benefit from the use of a graphical tool to reach new users and allow typical users to become more productive. This work presents such a tool for which several experiments were run to measure its usability with forty two users by having them perform a set of tasks for which their execution time, number errors and satisfaction were recorded. The tool reduced the previous average time required to completely define a set-play by 90% and enabled even non-expert users to use it. Moreover, users were on average satisfied with SPlanner having ranked it with a score of 77 (out of 100) using a System Usability Scale questionnaire.