Drones, factory robots, and other "edge" devices are drowning in data but starved of the computing power needed to make sense of it. Today’s communication networks treat every bit of data as equally important, designed to reconstruct messages perfectly rather than to extract meaning from them. This is wasteful for artificial intelligence, which cares about the *content* and *timeliness* of information—whether a drone’s video feed shows a fault, or a robot arm needs a command—not about flawless pixel-by-pixel transmission. This project aims to build a new communication paradigm from first principles, one where networks are designed specifically for machine learning. Instead of maximising data rates, the system would learn the best way to transmit only what an AI algorithm actually needs to make a decision. If successful, the work could transform how autonomous systems operate in the real world—enabling faster, more reliable control of industrial robots, real-time anomaly detection from drone footage, and ambient intelligence that works without a constant connection to the cloud. The research is fundamental, rooted in information theory and coding, but it is balanced with practical algorithm design aimed at tangible engineering products.
View original technical description
Intelligence is coming to the edge. Autonomous systems and industrial edge are the next targets of artificial intelligence (AI). However, despite impressive progress in hardware, edge devices do not have sufficient computing power and data to train and deploy state-of-the-art machine learning (ML) algorithms. Communication can allow edge devices to share their data and computational resources, and provide manifold increase in their learning capabilities, similarly to the impact language had on human intelligence. However, influenced by Shannon's seminal work, our current communication architectures are designed to establish reliable bit pipes between nodes, dismissing the relevance or utility of delivered bits. Yet, in ML applications, we are interested in inferring features of the underlying signals or messages, rather than reconstructing them. Increased data rates do not translate into faster or more accurate learning algorithms, and the content, timeliness, and the relevance of information are often more important than its quantity. AI-R challenges the current framework that treats communication and learning separately, striving to bridge this gap by developing an AI-oriented communication paradigm from fundamental theoretical principles. This new paradigm will go beyond the classical communication-theoretic framework by taking into account the ultimate goals of information transmission, for example, detecting anomalies in drone footage or remote controlling an industrial robot. AI-R will also step out of the cycles of incremental research in communications by fully exploiting AI capabilities to `learn' the best communication strategies to achieve the prescribed objectives. Building upon our expertise and recent contributions in information theory, coding, communications and ML, the project will balance fundamental research with application-oriented algorithm design and implementation to develop new engineering insights and products towards ambient edge intelligence.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know