|
Address: |
School of Computer Science |
|
|
Telephone: |
+44 121 414 6687 |
|
|
Fax: |
+44 121 414 4281 |
|
|
E-mail: |
||
|
|
|
|
|
|
|
|
|
|
|
Teaching Support Material: Graphics in Software Systems Components I, 2008-09
I am interested in a number of different fields of artificial intelligence (AI), but the unifying theme is reasoning under uncertainty. I believe consideration of uncertainty is the area of AI where the most significant recent progress has been made, and will prove to be an extremely important tool as AI techniques are applied in more and more real-world situations. My research can be broadly categorized into work on autonomy, planning, scheduling, diagnosis, and machine learning.
As well as my specific interests listed below, I am interested in the general problem of how to build autonomous systems. This includes problems such as how to interleave planning and execution, architectures for autonomy, state estimation in real-time, optimising resource usage in autonomous vehicles.
My interest in planning is mostly in using Markov decision problems (MDPs) to represent planning tasks in which there are actions with uncertain effects, multiple goals or rewards, and potentially uncertainty about the state of the system. I think one of the major contributions of AI has been to identify subclasses of general problems for which efficient algorithms exist. That is, to identify and exploit structure where it is present in problems. I am interested in finding efficient solution techniques for MDPs that have compact representations and hopefully also compact solutions.
I also have an interest in more classical approaches to planning, although still with uncertainty. In particular, I have worked on contingent planning problems, using techniques from graph-plan to generate heuristic estimates of the value of adding a branch at a particular point in a plan.
My interest in machine learning is largely been in the area of reinforcement learning, in particular in optimal exploration [5,6] and structured representations [7]. The exploration problem involves deciding between exploiting knowledge you already or exploring in the hopes of learning something that will let you do better in the future. The optimal exploration policy of a reinforcement learning problem can be defined as an MDP over the space of possible experiences. However, this MDP cannot be solved in practice. The work I have done in this area has been in trying to find heuristics that approximate a local solution to this exploration MDP .
My work in diagnosis of hybrid systems (discussed below) has left me with the strong impression that building models of these systems is a very hard problem. With this in mind, I have recently been looking at approaches to learn these models directly from data, perhaps with some input from the user to indicate which discrete mode of the system is generating a particular part of the data.
Uncertainty about resource usage is as much an issue in scheduling problems as it is in planning. An example of the kind of problem I am interested in is a space telescope that only transmits data to the ground at certain intervals, and must optimize its use of onboard storage for images, without knowing in advance how big a particular image will be after compression. Scheduling problems in which there are explicit models of uncertainty are a relatively new area in which there are many interesting problems to explore.
From 2000-2004 I worked in the Model-Based Diagnosis and Recovery group at NASA Ames Research Center. In that time I have seen a number of interesting diagnosis problems for which new techniques need to be developed. The area that interests me most is diagnosis of hybrid systems. The problem is to track the state of a system described in terms of both continuous and discrete variables. In principle, diagnosis on these models is simply Bayesian belief updating as observations arrive. However, this is rarely computationally feasible in practice. Instead my research has concentrated on doing Monte Carlo approximate belief update using particle filters. Diagnosis problems present some unique challenges for sample-based approximations such as particle filters, and most of my research in this area has been on overcoming those obstacles.
B.Sc. 1990 Victoria University of Wellington, New Zealand,
Computer Science.
B.Sc.(Hons.) 1991Victoria University of
Wellington, New Zealand, Computer Science.
M.Sc. 1994 University
of British Columbia, Computer Science.
My masters thesis was on structured representations of Markov Decision Process planning problems and efficient ways to generate approximate solutions.
Ph.D. 2000 University of British Columbia, Computer Science.
My doctoral thesis was on the uses of structure in planning and reinforcement learning, again concentrating on Markov Decision Processes as representations of the problems, and looking at how optimal policies could be discovered when the model of the problem is known (planning) and unknown (learning). I also worked on the exploration-exploitation problem in reinforcement learning.
2000-2004: NASA Ames Research Center
Acting Group Lead, Model-Based Diagnosis and Recovery group, NASA Ames Research Center (approx. 15 people in group) (2002-2004)
PI for Intelligent Systems seed project Investigating Fault Detection, Identification and Recovery for Drilling.
PI for Intelligent Systems project Probabilistic Fault Detection for Hybrid Discrete/Continuous Systems.
PI for Mars Technology Program project Real-time Fault Detection and Situation Awareness for Rovers.
Member of the team that proposed an autonomy demonstration mission to the Space Technology 7 mission selection process.
PI for Directors Discretionary Fund project Measuring the Resilience of Advanced Life Support Systems.
Co-I for Intelligent Systems project Contingency Planning.
Co-I for Mars Instrument Development Program project Drilling Autonomy for Mars Exploration.
Member of the Preliminary Design Review panel for the Astrobiology Science and Technology for Exploring Planets project Mars Analog Research and Technology Experiment.
I run a lot. I run mountain marathons (two day adventure races), orienteer, and occasionally fell run. I don't like running on roads. I also play Ultimate Frisbee, although not as often as I used to, ski, SCUBA dive, hike whenever and wherever possible, and generally spend as much of my time as possible outdoors. I'm also interested in photography (particularly nature and underwater photography), juggling, other "circus skills", archeology, and a wide variety of other things that I'll expand on in the future.
 |
 |
