Shared Semantic Representations for Coordinating Distributed Robot Teams

摘要

Most physically implemented multi-robot controllers are based on extensions of behavior-based systems. While efficient, such techniques suffer from a paucity of representational power. Symbolic systems, on the other hand, have more sophisticated representations but are computationally complex and have model coherency issues. In this report, the authors describe HIVEMind (Highly Interconnected Verbose Mind), a tagged behavior-based architecture for small teams of cooperative robots. In HIVEMind, robots share inferences and sensory data by treating other team members as virtual sensors connected by wireless links. A novel representation based on bit-vectors allows team members to share intentional, attentional, and sensory information using relatively low-bandwidth connections. The authors describe an application of the architecture to the problem of systematic spatial search. (5 tables, 11 figures, 25 refs.).