Prof. Fernando Manuel Ferreira Lobo Pereira (University of Porto, Institute for Systems and Robotic Porto, Portugal)
Keynote: Advanced optimization-based approaches for the control synthesis for Autonomous Underwater Vehicles
Systems of autonomous – air, surface, and underwater – robotic vehicles are increasingly regarded as an option of choice to gather data to respond to an increasingly wider range of societal needs in science, environment, exploitation of natural resources (geologic and biomass), surveillance, security, defense, and leisure. LSTS – The Laboratory of Underwater Systems and Technologies (https://lsts.fe.up.pt/) of Faculty of Engineering of Porto University has, over the years, been devoting a very significant R&D effort to the advancement of theoretical research in systems and control, as well as technologies to design and build such systems. The notorious achievements that gained worldwide visibility makes LSTS a reference institution with a consolidated leadership in many key niches of the pertinent very interdisciplinary contexts.
In this talk, I will focus on issues specific to the control of Autonomous Underwater Vehicles (AUVs) in either stand alone or formation modes. More specifically, a computationally efficient architecture to control formations of AUVs is presented and discussed. The proposed control structure enables the articulation of resources optimization with state feedback control while keeping the onboard computational burden very low. These features are critical for AUV systems as they operate in contexts of scarce resources and high uncertainty or environmental variability. The hybrid nature of the controller enables different modes of operation, notably, in dealing with unanticipated obstacles. Optimization and feedback control are brought together in a novel Model Control Predictive (MPC) scheme constructed with pre-computed Attainable Sets and Value Functions by taking advantage of the time-invariance subsystems and leaving to the real–time context, adaptivity operations requiring relatively low computational burden.
BIO: Fernando Manuel Ferreira Lobo Pereira (http://paginas.fe.up.pt/~flp/) is a Full Professor at Porto University, Faculty of Engineering, Electrical and Computer Engineering Department (http://www.fe.up.pt), Director of the Institute for Systems and Robotic Porto, (https://www.isr.uc.pt/isr/), Scientific Coordinator of FCT R&D unit SYSTEC (http://systec.fe.up.pt).
Academic degrees, fields of study, awarding institutions, dates in reverse chronological order: Received the Habilitation (“Agregação”) title from Porto University in 1997; Received the PhD in Control Theory from Imperial College of Science and Technology, London University, in 1986; Graduated in Electrical Engineering, Automation and Control at the Faculty of Engineering of Porto University in 1981.
Main scientific and technical area of research: Control and Optimization Theories (Non-smooth Analysis, Dynamic Optimization, and Impulsive Control), Hybrid Systems, and Coordinated Control, and their application in the control of autonomous and/or networked systems arising mainly in multiple robotic vehicle systems. The main application areas are: oceanography, and environment monitoring and surveillance, as well as data gathering for scientific marine research.
Selected recent R&D projects:
EMSO-PT – European Multidisciplinary Seafloor and Water Column Observatory-Portugal, Ref. 22157, POCI – P2020 – FEDER, http://www.emso-eu.org, 2017 – 2020.
ENDURANCE – Sistema baseado em veículos autónomos para observação oceonográfica de longa duração, Ref. 017084, P2020 – 33/SI/2015, http://lsts.fe.up.pt/our-work/projects, 2017-2019
E-URready4os – Expended Underwater Robotics Ready for Oil Spill, Ref. 2016/PREP/21, ECHO – European Commission, http://www.upct.es/urready4os, 2017-2018
FIRE-RS – wildFIRE Remote Sensing, Ref. SOE1/P4/E0437, INTERREG – ERDF, 2016 – 2019
STRIDE – Smart Cyberphysical, Mathematical, Computation and Power Engineering Research for Disruptive Innovation in Production, Mobility, Health, and Ocean Systems and Technologies, Structured RDI Projects – N2020, 2016-2019
MARINFO: Integrated Platform for Marine Data Acquisition & Analysis, Structured RDI Projects – N2020, 2016-2019
TOCCATA – Theory, Applications, and Numeric Computation in Optimal Control, Ref. PTDC/EEI-AUT/2933/2014|16858, FCT, 2016 -2019
Society and Technical Committees membership: IEEE, SIAM, APCA, AMS, INFORMS, SPM, and OE, IFAC Technical Committee on Optimal Control.
Published more than 300 publications in peer-reviewed journals and conferences.
Prof. Ivan Zelinka (Technical University of Ostrava, Czech Republic)
Keynote: Evolutionary Algorithms In Modern Engineering Problems and Solutions
Recent Advances and Progress
This keynote is focused on recent progress in design and use of evolutionary algorithms. Based on our research and research of various scientists worldwide it has been shown and experimentally demonstrated on many evolutionary algorithms, that it is possible to use them in wide spectra of practical applications as well as the solution of hard theoretical research problems.
The lecture will be focused on selected evolutionary algorithms, its basic principles, and its classification. After the introduction of basic principles of evolutionary algorithms will be discussed some physical limits of computing and algorithms. In the second part will be briefly described selected applications as the swarm robot control, plasma reactor control, chaos synthesis, control and identification, the evolutionary design of control law for a robot, evolutionary structure synthesis (math formulas, electronic circuits, logical functions,…), Darwinian evolution of computer viruses and swarm malware, amongst the others.
BIO: Ivan Zelinka (born in 1965, ivanzelinka.eu) is currently associated with the Technical University of Ostrava (VSB-TU), Faculty of Electrical Engineering and Computer Science. He graduated consequently at the Technical University in Brno (1995 – MSc.), UTB in Zlin (2001 – Ph.D.) and again at Technical University in Brno (2004 – Assoc. Prof.) and VSB-TU (2010 – Professor). Prof. Zelinka is responsible supervisor of several grant types of research of Czech grant agency GAČR as Unconventional Control of Complex Systems, Security of Mobile Devices and Communication ( a bilateral project between Czech and Vietnam) and co-supervisor of grant FRVŠ – Laboratory of parallel computing amongst the others. He was also working on numerous grants and two EU projects as a member of the team (FP5 – RESTORM) and supervisor (FP7 – PROMOEVO) of the Czech team. He is also head of research team NAVY http://navy.cs.vsb.cz/. Prof. Zelinka was awarded by Siemens Award for his Ph.D. thesis, as well as by journal Software news for his book about artificial intelligence. He is a member of the British Computer Society, Machine Intelligence Research Labs (MIR Labs – http://www.mirlabs.org/czech.php), IEEE ( a committee of Czech section of Computational Intelligence), a few international program committees of various conferences, and three international journals. He is also the founder and editor-in-chief of a new book series entitled Emergence, Complexity, and Computation (Springer series 10624, see also www.ecc-book.eu).
Prof. Askhat Diveev (Federal Research Center “Computer Science and Control” of Russian Academy of Sciences, RUDN University, Russia)
Keynote: Comparison of artificial neural networks and symbolic regression for synthesis of intelligent control systems
Specific aspects of the numerical solution of the control synthesis problem by the artificial neural networks and symbolic regression are considered. It is shown that artificial neural networks can be seen as one of the methods of symbolic regression with a given structure when symbolic regression comprises parametric optimization. To effectively solve the synthesis problem by the artificial neural networks, it is necessary to have a training sample. It is proposed to use as a training sample the results of multiple numerical solution of the optimal control problem for various initial conditions. Examples of control synthesis for a group of robots by the methods of artificial neural networks and symbolic regression are given.
BIO: Askhat Diveev (born in 1954 in Magadan, USSR), Doctor of Technical Sciences, Professor. He graduated from the Bauman Moscow State Technical University (BMSTU) in 1980, in 1989 defended a Candidate thesis in BMSTU, in 2001 he became a Doctor of Technical Sciences in Dorodnitsyn Computing Center of the Russian Academy of Sciences, in 2009 he became a Professor. Main scientific results are following: a new method of symbolic regression for numerical solution of the control synthesis problem called the network operator method (2006), a method of small variations of the code of the basic solution for the optimal solution search in non-numerical space (2006), a theory of controllable networks for traffic flow control models based on network configuration change (2008), new methods of symbolic regression based on modifications of known methods of symbolic regression: variational genetic programming (2014), variational analytical programming (2015), binary variational genetic programming (2016), complete binary variational genetic programming (2017).
Prof. Stanislav Vassilyev (Member of RAS, Institute of Control Sciences of RAS, Lomonosov Moscow State University, Russia)
Keynote: Intelligent control of autonomous and anthropocentric onboard systems
Buzikov M.E., Galyaev A.A., Guryev Yu.V., Titov K.B., Yakushenko E.I., Vassilyev S.N.
A hybrid technology of intelligent control of autonomous and anthropocentric onboard systems is proposed. It is based on non-clausal prover for automated reasoning and combines a symbolic knowledge representation, a processing with neural network pattern recognition, a numerical predictive modeling of physical processes in control object and its threat environment as well as with analytical methods of optimal control. If a control task is not provided with all necessary means of its solving, then the prover is able to deduce conditions for the task solvability and to ask another intelligent agents for the missing means to continue the control task solving (e.g., some digital means from the operator of onboard system). Applications to motion control problems in threat environments are examined.
BIO: Stanislav Vasiliev (born in 1946 in Thorez of Donetsk region, USSR), Doctor of Sciences in Physics and Mathematics, Member of the Russian Academy of Sciences, Chief researcher of the Institute of Control Sciences of RAS, Head of department of the Lomonosov Moscow State University. In 1964 he graduated from school No 6 in Kazan (with a gold medal), in 1970 – the Kazan Aviation Institute named after A.N. Tupolev (with honors and a recommendation for postgraduate education). In 1975 he was invited to the Department of the Theory of Systems and Cybernetics, organized in Irkutsk (at the Siberian Energy Institute of the USSR Academy of Sciences, on the basis of which in 1980 the Irkutsk Computing Center of the Siberian Branch of the Academy of Sciences of the USSR was established, reorganized in 1997 into the Institute of System Dynamics and Control Theory of the SB RAS. He worked as the head of the laboratory, the head of the department, the deputy director for scientific research, since 1991 – the director. He defended his dissertations on specialities “Mathematical cybernetics” and “System analysis and automatic control theory”. Since 1997 he is a Corresponding member of RAS and since 2006 – an Academician of the Russian Academy of Sciences on speciality “Control processes”. In 2006 he was elected a Director of the Institute of Control Sciences of RAS. Activities of the institutes headed by S.N. Vasiliev have always been highly evaluated by the Commissions of RAS.
S.N. Vasiliev is the author and co-author of more than 400 scientific works, including 14 monographs. Research directions developed by him are artificial intelligence and intelligent control, mathematical system theory, digital economy technologies. S.Vassilyev is the author of the priority results in the field of knowledge presentation and processing. He proposed methods for automatic theorem proving with applications for the intelligent control of dynamic systems. He developed methods for solving logical equations with applications for machine synthesis of theorems on analogies of mathematical models, including the theorems in terms of Lyapunov functions and morphisms. In co-authorship with his students, he proposed models and methods of multi-criteria decision-making with minimum requirements to a priori information, methods for harmonizing the interests of the parties in the problems of modeling and development of systems of ecological, economic and other nature. The models and methods formed the basis for original intellectual software products in the field of automation of research, design and control.
S.N. Vasiliev was repeatedly invited to the leading foreign research centers and universities for lecturing and working in joint scientific projects. For many years he was the head of a number of scientific topics, including. international grants. He established and headed the leading scientific school on stability and control in heterogeneous models of dynamic and intelligent systems. He was repeatedly invited with plenary reports to authoritative Russian and international conferences. He is the organizer of several such conferences.
S.N. Vasilyev conducts long-term pedagogical work. In 1976-2006 he worked as a professor and head of the departments of Irkutsk and Buryat State University, head (2007-2009) and professor (2009-2016) of the department of MIPT. Since 2009, he is the head of the Department in the Moscow State University. He has prepared more than 20 Candidates and Doctors of Sciences. In 2005-2015 years he was the Member of the Expert Council of the Higher Attestation Commission. He is the Chairman of the Dissertation Councils at the Institute of Control Sciences of RAS.
He conducts a great scientific and organizational work. He is a member of the Bureau of the Department of Energy, Mechanical Engineering, Mechanics and Control Processes of the Russian Academy of Sciences and the Bureau of the Commission of the Presidium of the Russian Academy of Sciences on the improvement of the structure of scientific organizations under the Federal Agency of Scientific Organizations of Russia, the chairman of the Scientific Council of the Russian Academy of Sciences on the theory of control processes and automation, co-chairman of the Scientific Council of the Russian Academy of Sciences on the methodology of artificial intelligence; chairman of the Russian National Committee for Automatic Control and the Commission of the Russian Academy of Sciences for Monitoring and Evaluation of the Performance of State Scientific Organizations and Educational Organizations of Higher Education of Russia, a member of RAS Council for Defense Studies, the Scientific Publishing Council of RAS, the Commission of the Presidium of RAS for Forming the List of Basic Research Programs of RAS, Expert commissions of the Russian Academy of Sciences on the gold medal of the RAS named after S.P. Korolev and the Prize of the Russian Academy of Sciences after B.N. Petrov et al.
Editor-in-chief of the journal “Automation and Remote Control” of RAS; deputy editor-in-Chief of the journal “Reports of the Academy of Sciences”; member of the editorial board of “Proceedings of RAS. Theory and Control Systems”, “Information and Computer Technologies Bulletin”, “Control Problems”, “Underwater Research and Robotics”, “Nonlinear Studies”, “Mathematics in Science, Engineering and Aerospace”, “Nonlinear Dynamics and Systems Theory”, “Journal of Automation and Information Science”, “Numerical Analysis and Applications”; member of the editorial review boards of “Information Technologies and Computer Systems”, “Artificial Intelligence and Decision Making”, “News of Higher Educational Institutions. Aircraft equipment”, etc.
S.N. Vasiliev was awarded the title of laureate of the USSR State Prize in Science and Technology (1984), the Prize of the Government of the Russian Federation in the field of education (2010), the Government Prize in Science and Technology (2012) and the Prizes of RAS in Basic Research, the Orders of Honor, Friendship and other state and scientific awards, letters of recognition and gratitude.