[fgcozman@usp.br]

Welcome to Fabio Cozman's Home Page

Who I am:

• Fabio Gagliardi Cozman, Full Professor at the Engineering School (Escola Politénica) at University of Sao Paulo, Brazil. I work in the Department of Mechatronics and Mechanical Systems.
• Director of the Decision Making Lab, where I conduct my research.
• I am from Sao Paulo, Brazil. I took Electrical Engineering at University of Sao Paulo. I then worked at the University on an Autonomous Mobile Robot; as a result, I got a master in Engineering. I went to the Robotics Institute at Carnegie Mellon University. My advisor was Eric Krotkov, the Great. I was in the VASC group, working with the Lunar Rover project, and more specifically in the Viper system. I finished my PhD there and returned to the University of Sao Paulo.
• I like to play tennis, and used to play some soccer; while at CMU, I used to play soccer with the Robotics team, the Viking Death Rats. I was captain of the team for four years (we were Intramurals champions in 1995). I also like to read, particularly French and Russian literature of the ninenteenth century, but I have not been able to read much since my son was born.
• Maybe you should look at some of my publications (there is a list of selected publications and a complete list of publications); and also at the errata.

Research:

• In my work on the theory of sets of probabilities, I explore inference and decision-making when probability values are indeterminate/imprecise. You can take a look at the web site of the Society for Imprecise Probability Theory and Applications (SIPTA); I'm a founding member of this society and currently I'm the society's newsletter editor. In this web site you will find information about several symposia on the theme of imprecision and indeterminacy in probability values.
• Regarding probabilistic reasoning, I have mostly worked with Bayesian networks (developing algorithms, generation methods, learning algorithms, classification techniques, applications in medical and embedded systems). The JavaBayes system is my implementation of Bayesian Networks in Java. The system is distributed under the GNU license; take a look at it and enjoy the system. A related item is the Interchange Format for Bayesian networks.
• Apart from these issues, I have worked in a variety of problems, mostly in Robotics and Artificial Intelligence; in the past I have been particularly involved with mobile robots and their sensors. A nice piece work was the development of robotic devices for the disabled; one of my students got a prize from the Brazilian Association for the Mechanical Sciences as Best Thesis (Master Level) in Brazil in 2003, for work on this device.