ICARA 2006 Keynote Speakers
Professor Emil M Petriu
Emil M Petriu, FIEEE, is a Professor and University Research Chair in the School of Information Technology and Engineering (SITE), University of Ottawa, Canada
He received his DiplEng and DrEng degrees in Electrical Engineering from the Polytechnic Institute of Timisoara, Romania, in 1969 and 1978 respectively. In 1979 he held a UNESCO postdoctoral scholarship for a three-month research term in the Department of Applied Physics at the Technical University of Delft, The Netherlands. He is a Registered Professional Engineer in the Province of Ontario, Canada.
Since 1985 Dr Petriu has been a faculty member in the Department of Electrical and Computer Engineering and then in SITE at the University of Ottawa. On half year sabbatical leaves, he has been visiting researcher at the Canadian Space Agency (1992), visiting professor at the Research Institute of Electronics, Shizuoka University, Hamamatsu, Japan (1994), visiting researcher at the Communications Research Centre, Ottawa (2002), and visiting professor at the Institute of Electrical Measurement and Measurement Signal Processing, Graz University of Technology, Austria (2003).
Dr Petriu has supervised 59 graduate students and 11 postdoctoral fellows and research engineers. He has published 65 refereed journal papers, 155 papers in refereed conference proceedings, authored two books, edited two books, and received two patents.
Dr Petriu has served as a member of the Administrative Committee (1996-2005) and Vice President (2000-2002) of the IEEE Instrumentation and Measurement Society. He is serving as chair of the TC-15 on Virtual Systems, co-chair of the TC-28 Instrumentation and Measurement for Robotics and Automation and co-chair of the TC-30 Security and Contraband Detection of the IEEE Instrumentation and Measurement Society.
In recognition of his contributions to the engineering profession, in 2000 he was elected Fellow of the Engineering Institute of Canada and in 2001 he was inducted as Fellow in the Canadian Academy of Engineering. In 2001 he was elected Fellow of the Institute of Electrical and Electronics Engineers (FIEEE). He received the 2003 IEEE Instrumentation and Measurement Society Award "for outstanding contributions to the theory and practice of robot sensing and perception."He was a co-recipient of the prestigious 2003 IEEE Donald G Fink Prize Paper Award, the unique paper award presented by IEEE in that year.
In 2004 Dr Petriu received a University Research Chair at the University of Ottawa, in Ubiquitous Computing Technologies for e-Society: Smart Houses and Other Intelligent Appliances.
Robotic Sensor Agents
ICARA 2006 Keynote Address - Abstract
This presentation will discuss a new generation of intelligent autonomous wireless Robotic Sensor Agents (RSA) for monitoring complex unstructured environments. Monitoring the environment, in practical terms, is a game with limited resources. There is a limited number of RSAs, which have limited operational parameters, communicating via a limited quality of service wireless communication network. RSAs should be capable of selective environment perception focusing on parameters that are important for the specific task and avoid wasting resources on processing irrelevant data.
Human-to-human communication and cooperation require a common language and an underlying system of shared knowledge and common values. In order to achieve a similar degree of machine-to-machine RSA interaction and cooperation, a RSA social framework should be available for the management of heterogeneous functions and knowledge for a large diversity of RSAs.
All RSAs are by definition instinctive information seeking agents. When the RSA deployment costs are prohibitive, these sensor agents would benefit from having survival behaviour/instinct, cooperation skills, adaptation and learning abilities. Like any sentient human being, the intelligent RSAs "bots" may have their own artificial personality.
Cooperating agents should be able to work together with other RSAs toward the overall goal, which is to maximise the information acquired from the environment. An evolutionary mechanism will allow a RSA to pass over to other descendent RSAs the learning experience and behavioural genes it acquired while operating in the field.
In order to allow for bot species survival RSAs should be able to cannibalise/recycle other agents that are operationally dead, which otherwise will be abandoned in the field. Providing RSAs with such a behaviour would allow for the upgrading of the operational capability of surviving agents.
An intriguing and controversial question is the value of extending the recycle_the_dead (i.e. the useful) cannibalism of RSAs to a more aggressive big_fish_eats_smaller_fish survival of the fittest behaviour. Obviously, such an aggressive survival behaviour should not allow for suicidal actions. An agent should not prey on equally strong or more powerful RSAs. While such behaviour may lead to more individually efficient RSAs through an evolutionary process, it may affect the global mission by decimating the population of agents deployed in the environment. It is quite possible that fewer more operationally efficient, from an information-gathering standpoint, RSAs will do a worse global job than a greater number of agents that may be less efficient but nevertheless still operational.
In order to facilitate recycling, each RSA has a status advertising mechanism telling other agents about its job-related functional qualification and health level. Heterogeneous RSAs cannot realistically be expected to talk exactly the same language. However, they will share domain-specific knowledge, which may be expressed by each of them in a different dialect. Accordingly, the communication management framework should define a domain specific semantic for common knowledge and functions. This framework is expected to act as a universal translator between speakers of different dialects.
In order to provide a flexible extensible open framework allowing for interoperability, methods should be developed to allow different agents to exchange the grammars describing their own dialects and to learn to understand each other. This way, the agents would be able to advertise their own functions, search and discover providers of required services, and express their needs in a collaborative environment.
Toshio Fukuda (M783-SM'93-F'95) received his BA in 1971 from Waseda University, Tokyo, Japan and his MS and DrEng from the University of Tokyo in 1973 and 1977 respectively. In 1977 he joined the National Mechanical Engineering Laboratory. In 1982 he joined the Science University of Tokyo, then joined Nagoya University, Japan in 1989.
Currently he is Professor of the Department of Micro-Nano System Engineering at Nagoya University, where he is mainly involved in the research fields of intelligent robotic systems, cellular robotic systems, mechatronics and micro- and nano-robotics. Dr Fukuda has been President of the IEEE Robotics and Automation Society (1998-1999), Director of the IEEE Division X, Systems and Control (2001-2002) and Editor-in-Chief of IEEE / ASME Transactions on Mechatronics (2000-2002). He was Founding President of the IEEE Nanotechnology Council (2002-2005) and President of SOFT, the Japan Society for Fuzzy Theory and Intelligent Informatics (2003-2005). He has received the IEEE Eugene Mittelmann Award (1997), the IEEE Millennium Medal (2000), the IEEE Robotics and Automation Pioneer Award (2004), the IEEE Robotics and Automation Society Distinguished Service Award (2005) and an award from the Ministry of Education and Science in Japan (2005). He is an IEEE Fellow (1995), an SICE Fellow (1995), a JSME Fellow (2001) and an RSJ Fellow (2004).
Advances in Robotics and Mechatronics for Human Support
ICARA 2006 Keynote Address - Abstract
Robotic and mechatronics technology can assist and support humans for more intelligent life: through physical assistance, sensor/actuation augmentation, skill assistance and intelligence enhancement. Many areas, such as industry, office, home, daily life, medicine and entertainment, can be dealt with by robotic and mechatronics technology for the safety, security and health of human beings.
Professor TAN Kay Chen
National University of Singapore, Singapore.
Associate Professor TAN Kay Chen received the B. Eng degree with First Class
Honors in Electronics and Electrical Engineering, and the Ph.D.
degree from the University of Glasgow, Scotland, in 1994 and 1997, respectively.
He is actively pursuing research in computational and artificial intelligence,
with applications to multi-objective optimization, scheduling, control, data
mining, and games.
Dr Tan has published 65 journal papers, 85 papers in conference proceedings,
co-authored four books including Multiobjective Evolutionary Algorithms
and Applications (Springer-Verlag, 2005), Modern Industrial Automation
Software Design (John Wiley, 2006), Evolutionary
Robotics: From Algorithms to Implementations (World Scientific, 2006),
and Neural Networks: Computational Models and Applications (Springer-Verlag,
expected in 2006), co-edited two books including Recent Advances in Simulated
Evolution and Learning (World Scientific,
2004) and Evolutionary Scheduling (Springer-Verlag, expected in 2006),
and a number of conference proceedings.
Dr Tan has been invited to give keynote and invited speeches in conferences.
He served as an international program committee member for 60 conferences
and involved in the organizing committee for 18 international conferences,
including the Technical Program Co-Chair for IEEE CEC 2005, Program Chair
for IEEE Conference on Cybernetics and Intelligent Systems 2004; 2006;
currently serve as the General Co-Chair for IEEE CEC 2007 to be held
in Singapore and the General Co-Chair for IEEE Symposium on Computational
Intelligence in Scheduling 2007 to be held in Hawaii. Dr Tan is currently
the Chairman of IEEE Computational Intelligence Chapter Singapore (Vice-Chairman,
2005), the Regional Member-at-Large (Asia and Oceania) for IEEE Computational
Intelligence Society, and a member of Board of Directors in Evolutionary
Dr Tan currently serves as an Associate Editor / Editorial Advisory Board
member of IEEE Transactions on Evolutionary Computation, International
Journal of Systems Science (Taylor and Francis, London), Recent Patents
on Engineering, and Journal of Applied Science. Dr Tan was a winner of
the NUS Outstanding Educator Awards (2004), the Engineering Educator
Awards (2002, 2003, 2005), and the Annual Teaching Excellence Awards
(2002, 2003, 2004, 2005).
Advances in Evolutionary Multi-objective Optimization: Algorithms,
Issues and Applications
ICARA 2006 Keynote Address - Abstract
Multi-objective evolutionary algorithms (MOEAs) are a class of stochastic
optimization techniques that emulates the Darwinian-Wallace principle
of "survival-of-the-fittest" in natural selection and adaptation
to solve multi-objective optimization problems.
Multi-objective (MO) optimization is a challenging task because it involves
the simultaneous optimization of several complex and conflicting objectives
in the Pareto optimal sense, and requires researchers to address many
issues that are unique to MO problems. The advances made in MOEAs are
the results of two decades of research, examining topics such as fitness
assignment, balance between exploration and exploitation, and elitism
in the context of MO optimization. This talk will discuss various issues
of evolutionary multi-objective optimization, including both the algorithm
developments and practical applications. It will also give a survey highlighting
the recent development trends and performance assessments of various
famous MOEAs in literature