 |
|
 |
| |
 |
| |
 |
| |
Presenter: David B. Fogel (President, the IEEE Computational Intelligence Society) |
(08:30AM - 09:30AM / Wednesday, December 16, 2009) |
| |
| |
Evolutionary computation has been applied to real-world problem solving for over 50 years. The evolutionary approach requires considering a variety of design decisions involving problem representation, variation operators, selection, population size, objective functions, and others. In this lecture, Dr. Fogel addresses some of the aspects of problem solving that he employs when addressing a problem from an evolutionary computing perspective. Aspects of mathematical theory about exploration and exploitation in search, as well as convergence rates, will be discussed as they apply to certain mathematical functions. Tools for assessing the effectiveness of alternative search operators and selection methods will be detailed. Finally, visualization of adaptive landscapes will be offered to assist in identifying different representations. Recombining the results of these analyses into a comprehensive picture of the problem can result in marked improvements in the quality of solutions and the speed in which those solutions are discovered. |
| |
Biography |
 |
David B. Fogel is the managing director of the Lincoln Vale Adaptive Strategies Group, which was formed in early 2008. He also serves as chairman of the board of Natural Selection, Inc., a company that applies evolutionary computation methods to challenging problems in United States defense and homeland security as well as providing solutions for industry and medicine. Dr. Fogel has served as a systems analyst at Titan Systems, Inc. (1984-1988), a senior principal engineer at ORINCON Corporation (1988-1993), and as an officer of Natural Selection, Inc. (1993-2008). Dr. Fogel received his M.S. and Ph.D. in engineering sciences with an emphasis on systems science from the University of California at San Diego in 1990 and 1992, respectively. He earned his B.S. in mathematical sciences with an emphasis on probability and statistics from the University of California at Santa Barbara in 1985. Dr. Fogel has written more than 200 publications, including 6 books, about evolutionary computation, neural networks, and computational intelligence. |
|
|
Dr. Fogel is the current president of the IEEE Computational Intelligence Society, a Fellow of the IEEE, and has received several scientific awards including the 2004 IEEE Kiyo Tomisayu Technical Field Award and the 2008 IEEE Computational Intelligence Society Evolutionary Computation Pioneer Award. He received an honorary doctorate from the University of Pretoria in 2008.
|
| |
| |
 |
| |
Presenter: Fakhri Karray (University of Waterloo, Canada) |
(08:30AM - 09:30AM / Thursday, December 17, 2009) |
| |
Major advances made over the past years in the areas of computational Intelligence, sensor fusion, intelligent man machine interaction, bio-inspired systems and neuroscience have made it possible to design new generation of intelligent robotic systems known as cognitive robotics. The increased interest in this field is mainly driven by the need for designing machines (robots in this context) that are able to interact with human very naturally and as much socially as possible, thus the new connotation of Social Robots. These new type of robots could be used for assistive tasks, for entertainment purposes and could be deployed in potentially hazardous and remote environment. Recent advances made in the field of cognitive systems and computational intelligence has made it possible to impart robots with new perceptual and context aware capabilities (humanoid systems). This is mostly done by endowing a machine with autonomous knowledge acquisition capabilities and automated reasoning mechanism allowing it to make high level decisions and respond adequately to previously unseen situations while being aware of its own existence and abilities (self-awareness) in achieving a particular goal. In this talk, we retrace the major milestones that led to the development of this emerging field and outline recent advances in developmental cognitive robotics, multi-modal attention, perception, reflectivity and social interaction. The talk also tackles recent application of cognitive robotics in areas such as assistive robotics and highlights the challenges encountered in developing cognitive systems that are truly human-like in terms of perception, adaptability and versatility. |
| |
| Biography |
 |
Fakhri Karray, received the Ph.D. degree from the University of Illinois, Urbana-Champaign, USA (89) in the area of Systems and Control. He is a Professor of Electrical and Computer Engineering at the University of Waterloo, Canada and the Associate Director of the Pattern Analysis and Machine Intelligence Laboratory. Dr. Karray has authored extensively in journals and conferences proceedings and holds thirteen US patents in various areas of intelligent systems. He is the co-author of a textbook on soft computing: Soft Computing and Intelligent Systems Design, Addison Wesley Publishing, 2004. Dr. Karray serves as the Associate Editor of a number of journals in his filed: the IEEE Transactions on Mechatronics, the IEEE Transactions on Systems Man and Cybernetics (part B), the IEEE Computational Intelligence Magazine, the International Journal of Robotics and Automation, the Journal of Intelligent Systems and Control, and the International Journal on Smart Sensing and Intelligent Systems. |
|
He has served as Chair/ co-Chair for more than 12 International Conferences and Technical Programs and served most recently as the General Co-Chair of the IEEE Conference on Logistics and Automation, China, 2008 and is the General co Chair of the International Conference on Systems, Circuits and Signals, Tunisia, 2009. Dr. Karray is the Waterloo Chapter Chair of the IEEE Control Systems Society and the IEEE Computational Intelligence Society.
|
| |
| |
 |
| |
| Presenter: Munsang Kim (Director, Center for Intelligent Robotics, KIST, Korea) |
(08:30AM - 09:30AM / Friday, December 18, 2009) |
| |
In recent years service robots have received a lot of attention from both industry and academia. They are individually designed to perform tasks in an unstructured environment for working with or assisting humans. Such robots thus have to be able to actively interact with potential users in their surroundings and to appropriately offer their services. It is essential for service robots to have a very flexible and well organized software framework in order to handle this kind of enormous and diverse information flow. In this talk robot intelligence architecture and it¡¯s corresponding knowledge base framework will be introduced, which are being developed for realizing practical robot intelligence at KIST. And efforts to make the software available as the reusable components for integration and to achieve error and exception handling methodology due to environmental diversity and complexity will be discussed. The proposed intelligent robot architecture was successfully applied to the intelligent robot platforms called Silbot and Ciros. Some video clips through the real experimental tryout will be also given during the presentation. |
| |
| Biography |
 |
Munsang Kim received the B.S. and M.S degree in Mechanical Engineering from the Seoul National University in 1980 and 1982 respectively and the Dr.-Ing. degree in Robotics from the Technical University of Berlin, Germany in 1987. Since 1987 he has been working as a research scientist at the Korea Institute of Science and Technology. He lead the Advanced Robotics Research Center since 2000 and became the director of the ¡°Intelligent Robot - The Frontier 21 Program¡± since Oct. 2003, which is one of the most challenging research programs in Korea. He is an invited professor at the Waseda University and Korea University since the year 2008 and 2000 respectively. He is serving as the editor for the Journal ¡°Intelligent Service Robot¡± and has served as Chair and co-Chairs for several international conferences. He is also serving as the Korean representative for the International Advanced Robotics Program since 2005. |
|
|
| His current research
interests are design and control of novel mobile manipulation systems, haptic device design and control, and sensor application to intelligent robots. |
| |
| --- |
|
| |
|
|
|
|
|
|
