Just as planning for AI must be responsive and opportunistic to a dynamic, complex environment, so should planning for organizations.  However, current project planning software is overly complex, brittle and rigid, thus plans once built are often abandoned or at least hopelessly incorrect and out of date.  A good tool would allow a manger to quickly update it in response to real-world contingencies.

We have had four undergraduate projects on this problem, two of which are under development now, and one of which got a distinction two years ago.  This project would involve reviewing the software of all these projects, choosing the most usable, evaluating its defficiencies and improving it.  Ideally you will work directly with real project planners in the testing, we have at least one (for Procter and Gamble) interested in the project.  This requires programming in java and/or python and dealing with other people's code, but will have a large usability, evaluation and documentation writing component.

This is a good project for a student interested in an industry job in applications.

This project builds on an existing system which uses a realistic emotional representation to control an 3D VR face, and a simple intelligent environment that is controlled through that environment.  The main focus of the project will be extending the intelligent environment, and testing its utility as an assistive technology, probably with a particular focus on early stages dementia patients. 

This is a good project for a student interested in an industry job in multi-media applications or HCI.  You will need to be unafraid of a large, complicated computing system: programming will mostly be building and testing interfaces but will include trying to make devices work with each other.  Note that the person who built the system is about to become a father so may not be very available!  But there are a couple other former students who may be available over email to support your efforts.  Testing and evaluation will be as important as programming in this project.

You will be using Behavior-Oriented Design (BOD), 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 VR avatars, language technology and vison or other sensing (touch screens, pressure sensors) to create a prototype system for helping support elderly users with failing memory.  It would helpful if the student  knew a little about vision or EE.  The prototype may focus on something easier, like taking typing breaks.  This would probably be done mostly in python, but you should not fear C.  It will involve ordering complexity, good time management, and being able to run extended experiments.

Both of these projects involve extending & analyzing existing agent-based models of social phenomena.  I am not certain it's a good idea to give these projects out, so you would really have to convince me you could do an excellent job & make a project of it.  I would be most likely to be convinced by someone coming from a strong science background.