Collaborating Authors


Bluebird hits the skies: Cambridge engineers developing AI system for air traffic control


Cambridge engineers will build a Digital Twin of UK airspace and a related machine learning system that collaborates with humans as part of a business-led research project supporting the Government's UK Innovation Strategy. The Prosperity Partnership is one of eight being supported with an investment pot of almost £60 million by the Engineering and Physical Sciences Research Council – part of UK Research and Innovation – businesses and universities. Professor Mark Girolami and Dr Adrian Weller are co-investigators of the collaborative research project titled Project Bluebird: An AI system for air traffic control. The vision is to deliver the world's first AI system to control airspace in live trials, working with air traffic controllers to help manage the complexities of their role. This system utilises digital twinning and machine learning technologies and includes tools and methods that promote safe and trustworthy use of AI.

MILP, pseudo-boolean, and OMT solvers for optimal fault-tolerant placements of relay nodes in mission critical wireless networks Artificial Intelligence

In critical infrastructures like airports, much care has to be devoted in protecting radio communication networks from external electromagnetic interference. Protection of such mission-critical radio communication networks is usually tackled by exploiting radiogoniometers: at least three suitably deployed radiogoniometers, and a gateway gathering information from them, permit to monitor and localise sources of electromagnetic emissions that are not supposed to be present in the monitored area. Typically, radiogoniometers are connected to the gateway through relay nodes. As a result, some degree of fault-tolerance for the network of relay nodes is essential in order to offer a reliable monitoring. On the other hand, deployment of relay nodes is typically quite expensive. As a result, we have two conflicting requirements: minimise costs while guaranteeing a given fault-tolerance. In this paper, we address the problem of computing a deployment for relay nodes that minimises the relay node network cost while at the same time guaranteeing proper working of the network even when some of the relay nodes (up to a given maximum number) become faulty (fault-tolerance). We show that, by means of a computation-intensive pre-processing on a HPC infrastructure, the above optimisation problem can be encoded as a 0/1 Linear Program, becoming suitable to be approached with standard Artificial Intelligence reasoners like MILP, PB-SAT, and SMT/OMT solvers. Our problem formulation enables us to present experimental results comparing the performance of these three solving technologies on a real case study of a relay node network deployment in areas of the Leonardo da Vinci Airport in Rome, Italy.

Optimal distributed testing in high-dimensional Gaussian models Machine Learning

The rapidly increasing amount of available data in many fields of application has triggered the development of distributed methods for data analysis. Distributed methods, besides being able to speed up computations considerably, can reduce local memory requirements and can also help in protecting privacy, by refraining from storing a whole dataset in a single central location. Moreover, distributed methods occur naturally when data is by construction observed and processed at multiple locations, such as for instance in astronomy, meteorology, seismology, military radar or air traffic control systems. The information theoretic aspects of distributed statistical methods have only been studied rigorously relatively recently. Most work up till now has focussed on distributed methods for estimating a signal in the normal-means model under bandwidth, or communication restrictions (see for instance [23, 6, 4, 7]) and, related to that, on deriving minimix lower bounds and optimal distributed estimation strategies in the context of nonparametric regression, density estimation and Gaussian signal-in-white-noise models (e.g.

How the Utilization of IoT is Benefitting the Airport Security


The digital networking of camera systems presents the prospects of improving the ways, where resources are used to design procedures efficiently and also reduce costs. FREMONT, CA: As per a research, firm Statista, there are more than 20 billion end devices that have been already networked through the Internet, and by the next year, the number will increase more than three times by. The end devices have become more intelligent and efficient, which is driven by the advancement conducted in artificial intelligence (AI), machine learning, and even 5G. IoT helps the cameras to assist the users in increasing their understanding of the behaviors of the passengers and employees. The knowledge about different technologies opens up new opportunities for advancing the procedures and reduces downtime.

A Bayesian Dynamic Multilayered Block Network Model Machine Learning

As network data become increasingly available, new opportunities arise to understand dynamic and multilayer network systems in many applied disciplines. Statistical modeling for multilayer networks is currently an active research area that aims to develop methods to carry out inference on such data. Recent contributions focus on latent space representation of the multilayer structure with underlying stochastic processes to account for network dynamics. Existing multilayer models are however typically limited to rather small networks. In this paper we introduce a dynamic multilayer block network model with a latent space represention for blocks rather than nodes. A block structure is natural for many real networks, such as social or transportation networks, where community structure naturally arises. A Gibbs sampler based on P\'olya-Gamma data augmentation is presented for the proposed model. Results from extensive simulations on synthetic data show that the inference algorithm scales well with the size of the network. We present a case study using real data from an airline system, a classic example of hub-and-spoke network.

Alphabet's drone delivery project Wing launches air-traffic control app

Daily Mail - Science & tech

Drone delivery service Wing is launching its own air-traffic control app to keep its craft safe in the skies. The company, owned by Google-parent Alphabet, recently started making deliveries in parts of Australia and Finland. Wing's new iOS and Android app aims to'help users comply with rules and plan flights more safely and effectively,' providing a rundown of airspace restrictions and hazards as well as events nearby that could interfere. The new app, Open Sky, is being released to drone flyers in Australia this month according to Wing. 'The design of our software has required a detailed understanding of flight rules -- along with buildings, roads, trees, and other terrain -- that allow aircraft to navigate safely at low altitudes, and we've used it to complete tens of thousands of flights on three continents,' Wing said in a blog post.

Tackling Climate Change with Machine Learning Artificial Intelligence

Climate change is one of the greatest challenges facing humanity, and we, as machine learning experts, may wonder how we can help. Here we describe how machine learning can be a powerful tool in reducing greenhouse gas emissions and helping society adapt to a changing climate. From smart grids to disaster management, we identify high impact problems where existing gaps can be filled by machine learning, in collaboration with other fields. Our recommendations encompass exciting research questions as well as promising business opportunities. We call on the machine learning community to join the global effort against climate change.

Floating Cell Towers Are the Next Step for 5G

IEEE Spectrum Robotics

As the world races to deploy speedy 5G mobile networks on the ground, some companies remain focused on floating cell towers in the sky. During the final session of the sixth annual Brooklyn 5G Summit on Thursday, Silicon Valley and telecom leaders discussed whether aerial drones and balloons could finally begin providing commercial mobile phone and Internet service from the air. That same day, Alphabet subsidiary Loon, a balloon-focused graduate of the Google X research lab, unveiled a strategic partnership with Softbank's HAPSMobile to leverage both solar-powered balloons and drones to expand mobile Internet coverage and aid in deploying 5G networks. No high-altitude network connectivity services have taken off commercially so far, but some Brooklyn 5G Summit speakers were optimistic that it would happen soon. "The opportunity is in our hands in terms of truly leveraging 5G in conjunction with the massive paradigm shift when it comes to UAS--drones--and also satellites," said Volker Ziegler, CTO at Nokia Bell Labs.

Can artificial intelligence make baggage tracking better?


IATA Resolution 753, which comes into effect this June, commits airlines to keeping track of baggage movements and aims to significantly reduce mishandled and misdirected bags. But it also creates new volumes of data, which SITA reports, could be handled more efficiently with AI tools like machine learning, robotics and predictive analytics. In a new report, Intelligent Tracking: A Baggage Management Revolution, SITA shares a vision of interconnected smart devices and applications that can inform each other of baggage movements with limited human intervention. By embracing new technologies and refining processes, the air transport industry has reduced its baggage mishandling cost from $4.22 billion to $2.1 billion over the past decade. The objective of Resolution 753 is to reduce that figure further, keeping passengers happy and protecting airlines from liability.