Dr. Joanna J. Bryson

Last modified: 16 August 2013

Dr. Bryson supervises two sorts of projects: AI projects, primarily those to do with making the design of AI systems easier, and NI projects, primarily those modelling the evolution of social and cognitive behaviour. NI projects often (but not always) include a systems-AI component, since the tools we use for modelling natural intelligence are all AI. Improving the AI or tools is one way to make the computer science component of the project clear. AI projects similarly will always have some interesting AI product to be produced.  Being your own user is also the best way to make sure your tools are actually useful.

See the AmonI software page for details of some of our existing projects, and related papers on the designing intelligent systems page.

Dr. Bryson meets with all her project students about every other week in Autumn term, and weekly in Spring. This is a group meeting, allowing students to experience peer supervising and supervision.  Students can work together on understanding common problems such as new technologies, though not on the projects or dissertations themelves. There are of course a few longer individual meetings at critical periods in both terms.  She sometimes accepts novel project proposals from strong students, and is happy to negotiate about and adjust her own proposals to the interests and capabilities of a particular student. However, please note that not every project below can be adjusted to suit every student's capabilities.

Previous projects and students.

Examples of possible AI projects for this year:

Generating Narrative Entertainment on Twitter using Tweetbots

The idea of this project is to transfer techniques from character-based computer game AI to the domain of Twitter, in order to create an engaging game entirely within the social domain with AI twitter bots.  In order to ensure multiple players can start the game at any time, much would have to be handled in DMs.  The game should probably be a romance or mystery.  It can be based on existing characters (so long as they are in the public domain, e.g. Jane Austen) or a narrative of the students own device.  Ideally the project would involve not only a proof of concept game, but also tools and guidelines for the development of such narrative games. It would probably use Behavior-Oriented Design (BOD), see for example Dragons, Bats & Evil Knights: A Three-Layer Design Approach to Character Based Creative Play.

A Behaviour Library for LEGO Robots

The department has a set of LEGO robots to be used by final-year students (mostly in the Spring). We would like to make them compatible with Behavior-Oriented Design (BOD) and to work with ABODE  (see above). Possible tasks include RoboCup Football, RoboCup Rescue a Robot Companion, or overcoming the Dalek problem in the East Building (the stairs.

Rapid Sketching with Combinatorial Search and Optimization

Note:  This is a special project to be done in collabroration with Adam Smith of University of Washington and Marina De Vos.  It requires very strong conventional programming skills and an interest in declarative programming.  Answer set programming (ASP) [http://en.wikipedia.org/wiki/Answer_set_programming] provides a declarative language for modeling complex combinatorial search and optimization problems. Current ASP tools are centered on command-line usage and provide no integrated support for visualization, debugging, and (more importantly) sharing solutions with others. We want to make a lightweight and accessible programming environment with integrated visualization akin to Sketchpad [http://sketchpad.cc/]. Such a tool would provide a very low barrier to entry for new users who might be exploring the artistic opportunities of declarative programming. Simultaneously, it would provide a means for advanced users to produce easy-to-share demonstrations of solutions to complex problems. We know how to run the core ASP tools inside of web browsers (Flash and HTML5) and we have examples of web-based creative coding environments for imperative languages. We need someone to put these two ideas together and help others get creative with this AI technology.

Creating a Bath Implementation of Behaviour Trees

Over the years, a lot of game & robot technology has been produced at Bath (& a few other universities) using POSH action selection.  However, there are other action-selection mechanisms (ASM) capable of describing dynamic plans.  One of the most widely cited presently is the Behaviour Tree (BT), however there is no canonical downloadable, open-source version of BTs.  This project would involve building a BT action selection mechanism.  Ideally this would be used to replace the POSH action selection on one of our existing behaviour libraries (e.g. UT Capture the Flag, Robocup Footbal, StarCraft: Brood Wars) so that the student would a) be easily able to compare the two technologies and b) not have to implement a substantial AI as well as building the ASM.

Improving the Action Selection Mechanism for an Artificial Football Team

Behavior-Oriented Design (BOD) is a way of making artificial intelligence based on combining object oriented design and proactive planning, normally using POSH action selection. Last year, Tom Hyde produced a good team for the Robocup Football Simulator League (that's VR, not robots), and in so doing identified some problems in the real-time scheduling for POSH. This project will probably be in Java, but other technologies are possible through an API. Note: this project requires a very competent programmer. Interest in sport is not particularly useful & could even get in the way!

Visualization and Maintenance of an Emotional Virtual Agent

Former PhD student Emmanuel 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 both develop and understand emotional AI systems.  This might very well involve reimplementing and simplifying EE-FAS system.

Extending & Generalising BOD Star Craft to more species and map.

Behavior-Oriented Design (BOD) is intended as an iterative methodology to make building AI easier and faster. In 2012, Simon Davies created a single BOD StarCraft or VR social spaces, such as Second Life. Can Davies' solution be refactored to make extending the AI to other maps and / or species easier?  This project would ideally create a number of additional extensions to.

Examples of possible NI projects this year include:

Determining the Structure of Emotion Space from Twitter Tweets

This project extends from an undergraduate dissertation by Eugene Bann on using simple vector-based automatic text analysis to create models of semantics. In particular, we are looking to see whether we can determine whether there is a discrete set of "basic emotions", or whether emotions are actually culturally-determined labels of locations in a vector space for affect. See this recent review in Trends in Cognitive Sciences to understand the issue–probably the answer is a combination of the two.  See also Eugene Bann's 2012 dissertation and other papers which started work on this topic but has diverged a bit.

Gamifying Social Simulation for Science Communication

Improving the public understanding of science is a significant goal of education generally and the current British government in particular.  The idea for this project is to create a process and possibly tools for extending scientific simulations into attractive platforms for citizen scientists and school students interested in understanding evolutionary social sciences.  The work extends from some of the active projects in my research group, such as Understanding Cultural Variation in Publc Goods Investment, or models of gossip, reputation and self deception.  The models for this work have been built by graduate students and postdocs on the simulation platform NetLogo.  This project would involve user studies to demonstrate effective, and requires an interest in the research topic and HCI as well as decent programming skills.  NetLogo provides tools and an API, and a project from 2012/13 by Michael Brooks, BODNetLogo, provides additional tools for extending agents, which should at a minimum help make it clear how to use the NetLogo API.

Modelling the impact of in-group & out-group assessments on regional economics

This project extends from a recent grant run in our group on Understanding Cultural Variation in Anti-Social Punishment. It would however require a new model, probably a spatial agent-based model, but a strong independent student could possibly look at this with game theory. 

page author: Joanna Bryson