HIVEMind: Grounding Inference in Cooperative Activity

Aaron Khoo and Ian Douglas Horswill

In this paper, we describe HIVEMind, a tagged behaviorbased 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. We describe an application of the architecture to the problem of systematic spatial search.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.