Deep learning for multi-technology fusion in industrial indoor asset localization and tracking

D'àmbit Europeu.

The increasing capabilities and performance of cyber physical systems are transforming industries and social environments. They enable us to solve increasingly challenging problems, relying on automation and exploiting AI to lead to services that improve quality of work and life. One of the key pillars of the digital revolution are indoor positioning technologies, with application in robotics, logistics, safety, security, and a large etcetera. In DUNE, we address deep learning aided positioning fusion mechanisms with the goal to deliver cost-effective and optimal indoor localization performance. Our models learn from diversified localization technologies and spatial sources to derive a real-time estimate of the asset's location. DUNE relies on far-edge, edge and cloud distributed computing capabilities to address real time application needs, functionally splitting the fusion methods to also meet the time, performance, and scalability needs. The outcomes of the project will be demonstrated using multiple localization technologies including AoA, BLE Beacons and LIDAR on a real scenario in which an industrial robot needs to be tracked.

Investigadors/ores

Filtra

Xavier

Vilajosana Guillén

Responsable

Borja

Martínez Huerta

Components en altres moments (1)

• Boquet Pujadas, Guillem 20222023