Coordinating Task Switching in a Robotics Multi-Agent System Using Behavior Trees

2026-05-31

AI Summary

This work addresses the challenges of multi-robot task coordination and behavior switching in dynamic environments, exemplified by the IEEE Very Small Size Soccer (VSSS) competition, by proposing a collaborative control architecture based on Behavior Trees (BTs). For the first time, BTs are introduced into the VSSS context to replace conventional finite state machines, substantially enhancing the flexibility of task transitions and the robustness of team coordination. Experimental evaluations conducted on the FIRASim simulation platform and in real-world competitions demonstrate that the proposed approach significantly outperforms existing methods in terms of coordination efficacy and match-winning rate.

Abstract

The application of multi-agent systems in robotics is a very challenging field. Several competitions involving such systems are proposed to foster research and development of strategies and mechanisms using games as the underlying domain. Among them are the ones from the \textit{IEEE Very Small Soccer (VSSS)} category, which is the case study described in this paper. In VSSS, two teams of three robots each compete in a very dynamic environment of a soccer game. Thus, coordination of robots' behavior during the game is crucial to win it. In this paper, we present a Behavior-Tree-based approach to support multi-robot coordination within the VSSS team of the ThundeRatz robotics team from the Universidade de S$\tilde{a}$o Paulo. Moreover, a comparison between the proposed approach and the previous one, which was based on a Finite State Machine (FSM), was conducted using the FIRASim simulator. Besides that, the performance of this new strategy was further evaluated in an academic robotics competition.

Problem

• multi-agent system
• task switching
• robot coordination
• behavior trees
• VSSS

Innovation

• Behavior Trees
• Multi-Agent Systems
• Task Switching
• Robot Coordination
• VSSS