School of Computer Science and Statistics
Balancing competing objectives, eg speed vs. safety, or efficiency vs. fairness, is a core challenge in multi-objective reinforcement learning (MORL). Prior work in my research group has shown how to optimize multiple objectives simultaneously without collapsing them into a single hand-weighted reward. But specifying the right trade-off between objectives numerically is hard: people often can’t … Read more
Recent work in my research group has shown that AI feedback can help balance competing objectives, like vehicle delay, emissions, and fairness across approaches, in traffic signal control, using preferences over individual decisions to guide reinforcement learning. However, decision-making in traffic control in sequential and long-horizon; a signal-timing choice that is suboptimal in the short-term … Read more
I lead the Applied Cryptography Research Lab in Trinity. Our research group works with a number of ledgers such as Hyperledger Besu, Ripple’s XRP Ledger (XRPL), Substrate, Zcash etc. I have a number of projects on offer as outlined below. You will need to become familiar with some advanced cryptographic primitives and networking techniques during … Read more
This idea will explore traffic signal control done by AI agents that negotiate in natural language: a vehicle requesting priority, a traffic light balancing competing demands, a neighbouring intersection protecting its own green-wave timing. This project builds the foundational system: a working prototype combining a traffic simulator (SUMO) with large language model agents that negotiate … Read more
Over the years I have found that many students who propose their own projects using computer vision have been very successful – probably because they are strongly motivated by the subject matter. So if you have an idea for a project in a field which interests you please contact me. The biggest issues are usually … Read more
Large language models can be used as autonomous agents that interact with applications through a browser, potentially allowing tests to be expressed as high-level goals rather than detailed scripts. This project’s vision is to investigate whether such agents can effectively explore and test web applications, and which factors affect their performance. The idea could be … Read more
Automated tests can sometimes become flaky, passing and failing across executions even when the software has not changed, reducing confidence in Software Testing and Continuous Integration. Recent studies have shown that web test flakiness can arise from factors such as asynchronous DOM interactions, timing assumptions, shared state, and test-order dependencies. The aim of this project … Read more
This project will investigate how artificial intelligence, including computer vision, can be used to support safer and more accessible navigation in urban environments. It will explore how information about the surrounding environment, potential hazards and contextual constraints can be combined to assess risk and provide appropriate, explainable assistance to users.
Reassembly of archeological artifact fragments requires considerable time and manual effort for researchers along with a necessity to handle potentially fragile material. It would therefore be advantageous for this process to be automatic. In this project we will work on creating a method for matching 3D scans of ancient animal bone fragments in order to … Read more
Can we tell something about a person from the way they move, even when their appearance has been completely changed? In this project, the student will use selected interactions from Meta’s Seamless Interaction dataset to create animated MetaHuman characters in Unreal Engine 5. Real conversational motion will be transferred onto virtual characters whose appearance differs … Read more