Implementation and Assessment of Robot Team Cooperation Models Using Deliberative Control Components
Résumé
This paper proposes an organizational framework and an approach for development of cooperation models for teams of Autonomous Adaptive Vehicles (AAV), using goal-driven control components. The framework and the approach are illustrated through the development and assessment of task allocation in multi-robot teams. Two cooperation models have been implemented: i) a team model based on the Adaptive Multi-Agent Systems (AMAS) theory, where task responsibility is agreed between team peers, by exchanging individual estimations of the degree of difficulty and priority to achieve the task; ii) a hierarchical model where an AAV manager asks team members estimations and then assigns the task. Experimentation for team-cooperation assessment has been done taking into consideration environmental changes, communications and internal failure. The most significant results reported in this work concerns team coordination in stressing situations. The experimental setting and team performance figures are detailed in the paper.
| Origine | Fichiers éditeurs autorisés sur une archive ouverte |
|---|---|
| Licence |