2006 Undergraduate Projects

Dr Joanna Bryson

jjb _AT_ cs.bath.ac.uk

Some of my older project pages have more links to relevant research. Also, I may have updated some of these projects. To check, look at Dr Bryson's projects page. Students who work with me should be relatively independent, although all my project students have a weekly group supervisory meeting and often wind up helping each other a little as well. I'm particularly interested in projects that go a little ways beyond my own current knowledge, so you will really have to do some research. On the other hand, the work you do may make a real difference -- your code could easily wind up on line or you may have a published paper. Undergraduates are a real part of my research programme. See my previous students page and the AmonI software page. More information on my research can be found on my web pages, especially my publications.

I am happy to listen to students' own project proposals so long as they have a lot to do with one of my research interests (which you can learn about on my web pages.) They must have a big artificial or natural intelligence component. I am not interested in databases! so don't even think about asking me to do a database project.

Adapting a Video Game to do Psychological Experiments

This project would involve conducting experiments in human implicit task learning through looking at how they perform in navigation and exploration tasks in a video game. You would need to modify a game (probably Unreal Tournament) to include three customized levels to correspond to the three phases of the experiment, and also to record statistics on the subjects, for example their route choices and their reaction times when faced with decisions. You would also need to conduct the experiments and write up the results formally.

Visualization and Maintenance of an Intelligent Virtual Agent

In a recently completed PhD project, Emmanul Tanguy built the Emotionally Expressive Facial Animation System (EE-FAS). The basic system is very modular, having been built on top of psyclone. However, understanding the architecture is not trivial for new users. This project would involve making it easier to see what EE-FAS is doing, and possibly to maniuplate the system. One way to do this might be to make a general GUI tool for enhancing the usability of psyclone. Another would be to focus on the emotion model of EE-FAS, showing their levels and interactions, allowing the interactions to be adjusted, or even for new basic emotions to be added. A truly exceptional project might do all these things.

The Behavior-Oriented Design of an Intelligent Environment

Behavior-Oriented Design (BOD) is an iterative methodology for building artificial intelligence. It is based on both object oriented design, dynamic AI plans and somewhat like extreme programming. Intelligent environments are rooms or houses that can sense and act, normally in support of human users. This project would involve combining an intelligent virtual agent (using EE-FAS, see above), existing language technology and a little (simple) vison to create a prototype system for helping support elderly users with failing memory. It would helpful if the student had taken or was taking vision courses, though really the level of vision needed is trivial (has a new blob entered the room? has it left?)

A Reactive Project Planner

Reactive planning is the way that intelligent systems can respond to a changing environment with appropriate actions. Project planning is the way managers try to make sure organizations do the same thing. Yet tools for project planning are seldom sufficiently reactive to address unexpected opportunities or unforseen problems. For example, a product may be found that eliminates many of the steps previously required by the project (though possibly adding some necessary integration), or a key employee may take another position, forcing massive rescheduling.

The purpose of this project is to create a tool that allows for the rapid sketching of a partially-complete project plan, as well as supporting changes and editing. The idea is to make a tool for dynamic, agile project management, not just for arachaic waterfall approaches. At any stage it should be possible to print a gannt chart.

A Competition Server for AI Gamebots Programs

Several universities, including ours, are usting Unreal Tournament to test theories of artificial intelligence. It would be helpful if there were a competition server so that AI programs could be stored, downloaded & compared with each other. This project would involve creating a fairly complicated system with a good deal of security. It would also involve learning enough about scientific experiments to help support those who want to run them and store their data. There are a number of similar sites (e.g. chess, machine learning, robocup) that would need to be reviewed as well.

The Behavior-Oriented Design of an Artificial Football Team

Behavior-Oriented Design (BOD) is a way of making artificial intelligence based on combining object oriented design and POSH reactive plans. Goals for this project include writing a critical analysis of BOD, testing and possibly improving on the IDE for BOD, ABODE, and of course creating a good team for the Robocup Football Simulator League (that's VR, not robots.) This project will be in python. Some work was done on this last year, so the basic code intergration is done, but not to the point that full games were played. This is a very time-intensive project. A real interest in robotics and AI is much more important than actual knowledge about football --- getting robots to pass is quite an accomplisment, never mind the world cup strategy!