One of the biggest challenges in humanoid robotics is not teaching robots how to walk, it is making them walk efficiently. This is the ambition behind the project led by Andrés González and Alexander Palatnik, winners of the Third Open Call of dAIEDGE.
Robots can perceive the world, but turning perception into safe and efficient action in real time remains a difficult engineering problem, especially when everything must happen directly on-device.
What if data, artificial intelligence models and computing power could be shared and monetised transparently, without relying on centralised platforms?
Vision Transformers have transformed the field of computer vision, delivering remarkable performance in image classification and understanding tasks. Yet their adoption at the Edge remains limited by a fundamental challenge: they demand significant computational power, memory resources and energy consumption.
Bringing intelligence closer to real-world interaction often means dealing with noise, uncertainty, and strict hardware limits all at once. That is exactly the space explored by NAVIR, the project developed by Mike Karamousadakis as part of the 2º Open Call of dAIEDGE.
Most AI models are evaluated as if they will run in ideal conditions. But real edge environments don’t work that way. That tension sits at the core of E*3, the project developed by Jorge Martínez during the Second Open Call of dAIEDGE.
In this edition, we feature Juan José Rodríguez Andina (University of Vigo) and Roberto Fernández (Logicmelt Technologies), winners of the Second Open Call, and their project QUAD.
Being identified and recognized within this European framework provides a strategic boost to continue evolving the platform, expanding its impact, and strengthening our ability to connect cutting-edge research with the real-world needs of society and industry.
