Pieter Buzing @ Delft University of Technology


This is me TU Delft
email: p.buzing@ewi.tudelft.nl
room: HB-09.040
tel: 015-2782507

My PhD research

The main topic of my research is to apply (and extend) methods of model based diagnosis to a multi-agent setting. More specifically, the problem of multi-agent plan-repair in a dynamic and error-prone environment will be addressed. In such environments autonomous planners have to detect future conflicts in their plans and coordinate appropriate repair actions. A prototypical implementation will be developed for an Air Traffic Control (ATC) case.

My research topic is part of a larger STW-funded project consisting of three research tracks, i.e. conflict detection (Maastricht University), agent communication (Utrecht University), and plan repair (Delft University of Technology).
Departure: september 2003
ETA: september 2007


Buzing P.C., Eiben A.E. and Schut M.C.,
Emerging Communication and Cooperation in Evolving Agent Societies.
Journal of Artificial Societies and Social Simulation, 2005. In press.

Pieter Buzing, Adriaan ter Mors, Jeroen Valk and Cees Witteveen,
Task Coordination for Non-cooperative Planning Agents.
Proceedings of the Second European Workshop on Multi-Agent Systems, (EUMAS 2005),
16-17 December 2004, Barcelona (Spain). pp. 87-98.

Pieter Buzing, Adriaan ter Mors and Cees Witteveen,
Multi-agent Plan Repair With DTPS
Proceedings of the 23rd Annual Workshop of the UK Planning and Scheduling Special Interest Group, (PlanSIG 2004),
20-21 December 2004, Cork (Ireland). pp. 3-14.

Pieter Buzing and Cees Witteveen,
Distributed (Re)Planning With Preference Information
In: Verbrugge R., Taatgen N. and Schomaker L., editors
Proceedings of the Sixteenth Belgium-Netherlands Conference on Artificial Intelligence, (BNAIC 2004),
ISSN: 1568-7805, 2004, pp. 155-162.
[pdf] [talk]

Buzing P.C., Eiben A.E., Schut M.C. and Toma T.,
Cooperation and Communication in Artificial Societies.
In: Greenwood G., editor, Proceedings of the 2004 Congress on Evolutionary Computation (CEC 2004),
IEEE Press, 2004, pp. 230-237.

Buzing P.C., Eiben A.E. and Schut M.C.,
Evolving Agent Societies with VUScape.
In: Banzhaf W., Christaller T., Dittrich P., Kim J.T. and Ziegler J., editors,
Advances in Artificial Life, Proceedings of the Seventh European Conference on Artificial Life (ECAL 2003),
Lecture Notes in Artificial Intelligence, vol. 2801, Springer Verlag, 2003, pp. 434-441.

Master's Thesis

VUScape: Communication and Cooperation in Evolving Artificial Societies (ps.gz, pdf, ppt)
Master's Thesis, Vrije Universiteit Amsterdam, 2003
This thesis presents a new model for empirical investigations of evolving agent societies in SugarScape-like environments. In particular we address the concepts of communication and cooperation. In this framework the researcher can specify parameters for both the agents' behaviour and the environmental conditions. The testbed environment allows detailed monitoring of emergent group behaviour. In this specific project we implemented a broadcasting communication scheme and introduced a cooperative pressure that is controllable by a single parameter. Also the SugarScape agents were extended with genetic communicative preferences, which enables the population to learn surviving behaviour through evolution. These preferences independently refer to active (i.e., sending of food signals) and passive (i.e., reception of food signals) communication. We observe that when the cooperative pressure increases the agents' communicative attitudes evolve towards more communication.

Student papers

Comparing Different Keyboard Layouts: Aspects of QWERTY, DVORAK and alphabetical keyboards(ps, pdf)
Human-Computer interaction course, 2003
Although developments in computer technology have been huge in the last fifty years the way we mainly communicate with the machine is still basically the same: the keyboard. Especially the layout of keys on a computer keyboard has had little revisioning. The QWERTY layout (which stemmed from the classic typewriter) can be considered the standard or "universal" design. This layout was chosen for mechanical reasons which don't apply for the modern keyboards. Many alternatives have been proposed, most notably the DVORAK system and the alphabetical ordering. The former was designed to help the expert user achieve maximum typing speed by placing the keys optimally, while the latter was supposed to support novice users by reducing search efforts.
This article gives an overview of the research that has been done concerning such comparisons. We conclude that the claimed Dvorak typing speed-up over QWERTY is rather limited and that unskilled typists can experience help from an alphabetically biased keyboard.

Multi-Document Summarization: Two Methods(doc, ppt)
FAAI course, 2001
In this paper we will discuss and compare two methods for multi document summarization. One approach is concerned with the explicit meaning of words and viewing them as concepts, who's (semantic) relations explicitly represent context. The second approach is more top-down in its attempt to identify the salient parts of the source documents. It starts at the paragraph level, which forms the base for further processing. After comparison we conclude that the second approach is slightly favorite.

Hybrid Systems: Two Examples of the Combination of Rule-Based Systems and Neural Nets(doc, ppt)
FAAI course, 2001
Neural networks and rule based systems both have their clear advantages as well as their disadvantages. Combining these two could lead to a powerful system that profits from the positive characteristics of each other. Fu(1989) and Towell & Shavlik(1994) each proposed such a hybrid systems. This paper gives a comparison between them and concludes that in both systems the inductive learning ability of a neural network can contribute to a knowledge base and that the semantic foundedness of a knowledge base can be a good starting point for a neural network.


The IIA-search engine project (by myself and Ruud Stegers).