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 listed here will necessarily 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 research interests are in intelligent decision making, particularly for cooperative, competitive and uncertain situations. A large part of my work is building simulators which allow us to test different algorithms and protocols. For example, how can a group of robot vehicles cross a busy junction? How should we guide a group of people on the fastest and safest way out of a building? 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?
Most of my research is carried out with 4C: the Cork Constraint Computation Centre. In particular, I am part of CTVR, a multi-site research centre in collaboration with Alcatel Lucent (Bell Labs), in which we are optimising the operation of wireless networks, ITOBO, a multi-disciplinary project looking at ICT for energy efficient smart buildings, and NEMBES, a research consortium based in Cork looking at the design, deployment, operation and applications of networked embedded systems.
Project List
KNB1: Distributed learning of pedestrian behaviour
In the Nembes project, we are designing Wireless Sensor Networks which interact with people passing close to the sensors. To be able to operate efficiently, the sensor network needs to learn the times and locations which see high pedestrian traffic . However the sensors and computing resources are resource limited. In this project we will build a multi-agent simulator which models the sensor network and pedestrian behaviour. We will then consider multi-agent learning algorithms which try to build a network-wide model of the patterns of movement. Other distributed algorithm projects are possible, including distributed channel selection for the radio nodes, or simulation of simple mobile sensing devices moving through an environment while collaborating as a team.
Requirements: You should be a confident programmer
- you will either code this from the beginning in Java, or link to
an existing simulator in java, or use a C++ network simulation tool.
You should also be interested in research, since the project will need
you to read current research papers and implement new algorithms.
KNB2: Android App development for user modelling
Allocated
In the Itobo project we are attempting to learn how people feel about the internal environment in buildings, so that we can improve the heating, ventilation and lighting control. We do this using software that runs on a user's PC. This project will look at developing a similar solution as an Android App, which will allow the user to describe their preferences in any location, and which will correlate this with known information on the phone.
Requirements: You must be a confident Java programmer
and be willing to explore the Android libraries to find out information for yourself.
KNB3: Autonomous Vehicle Simulation
Autonomous vehicles are now moving out from research labs onto real city streets (aaai.org/AITopics/AutonomousVehicles). Since these vehicles will come equipped with sophisticated sensors and wireless communication systems, we can change the way in which multiple vehicles interact with each other. Since the systems will be safety-critical, extensive simulation will be needed to understand how traffic management works and could be improved. In this project, we will look at multi-agent simulation of autonomous vehicles, and we will develop and study different protocols for vehicle interaction, selecting from, for example, protocols for changing lanes using vehicle-to-vehicle signalling, or scheduling for complex junctions using vehicle-to-controller communication.
Requirements: You must be a confident programmer, and
you must be interested in research - this project will require you to
read current research papers and to explore new ideas.