—The vision of network robot systems involves robots embedded in smart environments, with which they can collaborate and communicate. In such systems, robots have access to many different sources and types of information, which need to be coordinated and combined effectively. In this work, we propose a framework which addresses the problem of combining heterogeneous information in a network robot system. The approach is inspired by work on conceptual spaces and perceptual anchoring, and is implemented using tools from fuzzy logic.