Projects

KNB1 Car pooling and sharing with Genetic Algorithms
Allocated: Shane Hickey
KNB2 Multi-agent communication in search missions
Allocated: Christian O'Leary
KNB3 Dynamic flow algorithms for traffic control
Allocated: James Hannon
KNB4 Wireless localisation using RaspberryPis
Allocated: Alexey Shapovalov
KNB? Further student-proposed projects are welcome

Project suggestions are listed on the right. These projects are suitable for either 4th year projects, or for MSc projects. Each of these project areas can be turned into multiple different projects for different students, but there is a limit to the number of projects I can supervise, so not all projects are guaranteed to be allocated. You are also welcome to suggest your own project, if they match my general interests outlined below. It is best to contact me first by email (k.brown @ cs.ucc.ie).

My interests are in intelligent decision making, particularly for cooperative, competitive and uncertain situations. We also build simulators which allow us to test different algorithms and protocols. For example, how can a group of autonomous vehicles cross a busy junction? How do we guide drivers and passengers to get best use out of a car pooling scheme? How can a group of sensor nodes coordinate themselves to cover mobile targets? How should a network of radios share the radio frequency to ensure that all messages are delivered?

My research is carried out in Insight, the centre for data analytics, in which we work on coordinated optimisation in response to dynamically changing data. I am also a funded investigator in Connect, the future telecommunications research centre, in which we optimise the operation of wireless networks.

Project List

KNB1: Car pooling and sharing

Car pooling and car sharing schemes try to reduce congestion by encouraging people to share journeys. To make the most out of these systems, careful route planning is needed. Route planning algorithms can be integrated with optimisation techniques to make sure ride shares are balanced or meet other criteria - for example, to ensure eVehicles are sufficiently charged when required. This project will study one or more subproblems in ride-sharing - for example, matching riders to drivers, or allocating fleet vehicles to journeys. We can consider different solving techniques, including genetic algorithms or constraint programming.
Requirements: You must be a confident programmer, and you must be able to read current research papers.

KNB2: Multi-agent communication in search missions

There are many proposals for using platoons of autonomous vehicles, drones and mobile robots to carry out search missions and inspection tasks. Success in these schemes requires effective communication between the agents. In this project we will look at search task in a grid world, in which a platoon of agents explore the world looking for a target. Each agent has limited vision, and so agents must communicate with each other to avoid covering the same ground multiple times. We will explore the impact of different communication models on the search process, studying how we can trade-off search cost against communication delays. The project can be extended to include mobile targets, and uncertainty in the observations.
Requirements: You must be a confident programmer, able to implement graph algorithms, and you must be able to read current research papers.

KNB3: Dynamic flow algorithms for traffic control

Moving large numbers of vehicles around a road network efficiently is critical for daily congestion management in a city, but also for evacuation during emergencies, and for one-off event management. The problem can be modelled as network flow, but where some arcs cannot be used at the same time as others (e.g. lanes that cross in a junction), and so the flow solution must be dynamic - that is, it must specify different flow at different times. This project will develop some heuristic algorithms for managing volumes of traffic through a road network.
Requirements: You must be a confident programmer, able to implement graph algorithms, and you must be interested in research - this project will require you to read current research papers and to explore new ideas.

KNB4: Wireless localisation using RaspberryPis

Modern smart buildings can provide personalised services based on wireless actuation and the ability to locate a user precisely using wireless signals from a mobile device or wireless ID card. In this project, we will explore wireless localisation and service provision using a set of RaspberryPis augmented with WiFi receivers. The aim will be to explore how we can enable a network of the Pis to determine a precise location for a user, based on signals received from their smartphone. The project can be extended or adapted to other use cases.
Requirements: You must be a confident programmer, able to explore the Pi hardware and OS independently, and you must be interested in research - this project will require you to read current research papers and to explore new ideas.