Dynamic Collaboration Between Networked Robots and Clouds in Resource-Constrained Environments

Abstract—Underwater mobile sensor networks such as Au-tonomous Underwater Vehicles (AUVs) or robots are envisioned to enable applications for oceanographic data collection, en-vironmental and pollution monitoring, offshore exploration, and distributed tactical surveillance. These applications require running compute- and data-intensive algorithms that go beyond the capabilities of the individual AUVs that are involved in a mission. To execute these task-parallel algorithms in resource-and time-constrained environments, dynamic and reliable collab-oration between local networked robots (e.g., AUVs) and remote public Clouds is needed. To this end, the heterogeneous sensing, computing, communication, and storage capabilities of local and remote resources are exploited to form a “loosely coupled ” mobile Cloud, and a novel resource provisioning engine that dynamically takes decisions on “what ” and “where ” the tasks should be exe