Due to the growth of data generated by ever-growing Internet-of-things, roaming edge devices, connected operations, and multi-vendor Cloud ecosystems, the future computing paradigm will be heterogeneous, dynamic, and involving multiple autonomous entities. We refer to this paradigm of computing as Hybrid Cloud Ecosystems. Hybrid Cloud Ecosystems encompass wirelessly connected Internet-of-things (IoT) sensors, roaming edge devices such as drones and robots, edge clouds, regional data centers, and multi-cloud environments such as AWS and IBM Cloud.
Within Hybrid Cloud Ecosystems, our overall objective is to develop adaptive cyber-physical systems in which heterogeneous robot teams collaborate with humans and other robots to perform complex tasks in structured and instrumented industrial settings, such as factories and fulfillment centers. A key feature of such application domains is that they have access to a multi-layer, dynamically changing computational system as part of a Hybrid Cloud Ecosystem that can support proprietary or collaborative/shareable resources. Methods developed for structured industrial settings are the first step on the path to deployment of robotic assistants in office, commercial and home environments.
Part of the Hybrid Cloud & AI theme of the IBM-Illinois Discovery Accelorator Institute, this collaborative project brings together researchers from IBM and UIUC that span mobile computing, systems, parallel computing, robotics, computer vision, and natural language processing.