All Projects

Summary Multi-task learning (MTL) enables a single neural network to learn several related tasks simultaneously, such as image segmentation, attribute prediction, and object classification. Although MTL often improves efficiency and generalization, competing objectives from different tasks can produce conflicting gradients during training, resulting in negative transfer and degraded performance. Recent studies suggest that gradient interference … Read more

Summary: Autonomous UAVs are increasingly deployed in diverse environments such as urban areas, forests, construction sites, and agricultural fields. However, object detection models are typically trained offline using fixed datasets and often experience significant performance degradation when operating in unseen environments. Retraining the model from scratch whenever new data becomes available is computationally expensive and … Read more

This project investigates the application of agentic AI reasoning to the autonomous control and optimisation of wireless communication networks, leveraging the OCUDU platform in conjunction with an AI-native network controller. The student will extend the existing controller architecture to support closed-loop agentic control, wherein an AI agent autonomously issues configuration commands, observes network responses, and … Read more

1. Background and motivation As mobile networks evolve toward 6G, artificial intelligence is moving from an optional optimisation layer to the core control mechanism of the network itself: AI-native architectures increasingly rely on models embedded directly in the control loop (e.g., forecasting traffic, managing topology, orchestrating resources, and making real-time decisions across base stations and … Read more

1. Background and motivation Modern mobile networks are increasingly managed by AI agents rather than fixed rule-based controllers, for example, agents that read live network telemetry (throughput, latency, energy consumption) and issue configuration commands (transmit power, scheduling weights, cell sleep states) to meet operational goals. This is the paradigm behind O-RAN’s RIC (RAN Intelligent Controller) … Read more

1. Background and motivation “Deploy an AI model for network optimisation” is not a single, fixed cost: a traffic-forecasting model that runs once per minute per cell has wildly different compute requirements from an agentic reasoning loop that must diagnose a fault and propose a remediation within a sub-second RIC control-loop deadline, or from an … Read more

Background The next generation of smart cities will be powered by fleets of autonomous AI agents that continuously monitor, analyse and respond to events occurring throughout the urban environment. These agents may support traffic optimisation, emergency response, public transport coordination, environmental monitoring, digital citizen services and public safety applications. For these systems to operate effectively, … Read more

Background Modern AI systems are evolving from isolated models into networks of collaborating AI agents that work together to achieve complex goals. Examples include autonomous transportation systems, distributed robotics platforms, smart manufacturing environments and large-scale digital assistants. A key challenge is determining how these agents coordinate their behaviour while competing for limited computing resources across … Read more