CLEVER
Collaborative edge-cLoud continuum and Embedded AI for a Visionary industry of thE futuRe
Abstract
CLEVER proposes a series of innovations in the area of hardware accelerators, design stack, and middleware software that revolutionize the ability of edge computing platforms to operate federatedly, leveraging sparse resources that are coordinated to create a powerful swarm of resources. CLEVER technologies will support the deep edge computing paradigm, moving computing services closer to the end user or the source of the data to reduce power consumption, reduce capacity requirements, and latency for mission critical applications.
CLEVER will demonstrate processing solutions for AI at the edge through four use cases: (1) digital twin for in-factory optimization, (2) smart agriculture for high yield eco-farms, (3) fully automated material deployment, and (4) augmented reality for shopping sites.
CLEVER will overcome traditional limitations of edge computing in terms of limited resource availability by providing an effective framework for seamless use of federated resources in the edge-cloud continuum.
- definition of the architectural requirements and system functional specifications with particular focus on ensuring throughput, latency, and scalability of the edge nodes when running applications that need high-performance video processing.
- specifications for AI solution to be used in the Augmented Reality for shopping sites use case (UC4)
- use case definition and execution plan related to UC4
- focusing on the Intelligent Resource Management for AI applications related to UC4
- Subtask leader on the development of AI-based applications targeting UC4
- WP leader, will help ensure the necessary coordination between WP6 tasks
- Subtask leader on the use case demonstrator on augmented reality for shopping sites, building a demonstrator including holographic systems and video projection systems, in addition to crowd sensor capturing (i.e. video cameras) that will capture information to be processed at the edge through the collection of data from distributed sensors in the shopping site.