Instituto Politecnico Braganca (Portugal)
Global markets are imposing strong changing conditions for industrial companies running their businesses, facing strong pressures related to the customization of products in high flexible production systems. Industry 4.0 is an initiative that promotes the computerization of traditional industries, aiming intelligent factories characterized by adaptability, efficiency, functionality, reliability, safety, and usability, as well as the integration of customers and business partners in business and value processes. Cyber-physical systems constitute a technological basis to address this challenge, providing significant benefits in several emergent application domains, such as smart grids, smart buildings, smart transportation, smart healthcare, and particularly in smart manufacturing. This presentation discusses the use of multi-agent systems to support the development of intelligent, dynamic and self-* large-scale industrial cyber-physical systems. For this purpose, some successful industrial/research projects will be described, emphasizing the achieved results, the innovation of using agent-based solutions as well pointing out the current trends and challenges.
Paulo Leitão received the PhD degree in Electrical and Computer Engineering from the University of Porto, Portugal, in 2004. From 1993 to 1999 he developed research activities at the CIM Centre of Porto, from 1999 to 2000 at IDIT - Institute for Development and Innovation in Technology, and since 2009 at LIACC - Artificial Intelligence and Computer Science Laboratory. He is Professor at the Department of Electrical Engineering of the Polytechnic Institute of Bragança, Portugal, since 1995.
His research interests are in the field of intelligent & distributed manufacturing control, reconfigurable manufacturing systems, cyber-physical systems, multi-agent systems, holonic control systems, factory automation, and bio-inspired engineering.He participate / has participated in several national and international research projects (e.g. EU
H2020 PERFoRM - Production harmonizEd Reconfiguration of Flexible Robots and Machinery, EU FP7 ARUM - Adaptive Production Management, EU FP7 GRACE - InteGration of pRocess and quAlity Control using multi-agEnt technology, EU DEDEMAS - Decentralized Decision Making and Scheduling, EU MOSCOT - A Modular Shop Control Toolkit for Flexible Manufacturing, EU PASO - Paradigm Independent Shop Control for Smaller Manufacturing Sites, and EU CCP - CIM Centre of Porto), and Networks of Excellence (e.g. IMS - Intelligent Manufacturing Systems, and CONET - Cooperating Objects Network of Excellence). He is member of the International Program Committee of several scientific events, has published more than 160 papers in international scientific journals and conference proceedings (per-review), and co-author of three patents He received four paper awards at INFOCOMP’13, INCOM’06, BASYS’06 and IEEE INDIN’10, and served as co-chair of several international conferences, namely SOHOMA’16, ICARSC’16, IFAC IMS’10 and HoloMAS’11.
Dr. Leitão is Senior member of IEEE, member at large of the Industrial Electronics Society (IES) Administrative Committee (AdCom), chair of the IEEE Standards Association P2660.1 Working Group and past Chair of the IEEE IES Technical Committee on Industrial Agents.
National Institute of Informatics (Japan)
A cyber-physical system (CPS) is an integration of computation with physical processes with feedback loops where physical processes affect computations and vice versa by using IoT systems to monitor and actuate the physical process. Agent approaches, which have explored many studies so far, can have much contributions to CPS in addition to IoT. This talk surveys existing projects to bridge the real and cyber worlds by using agent-based approaches, in particular software-level ones, in addition to our projects. CPSs bring unique requirements to agents, e.g., long-term autonomy, for a week, month, and year, instead of any instant and single tasks. Therefore, reliability and adaptability become important, so software engineering for agents for long-term autonomy becomes key issues in agents in CPS, including IoT. The talk also discusses future software issues for agents.
Ichiro Satoh received his B.E., M.E, and Ph.D. degrees in Computer Science from Keio University, Japan in 1996. From 1994 to 1995, he was a visiting researcher of Rank Xerox Grenoble Laboratory. From 1996 to 1997, he was a research associate in the Department of Information Sciences, Ochanomizu University, Japan and from 1998 to 2000 was an associate professor in the same department. From 2001 to 2005, he was an associate professor in National Institute of Informatics (NII), Japan. Since 2006, he has been a professor of NII and now he also work as Deputy of Director General of NII. His current research interests include, distributed and agent computing. He also work as technical chairs and members of governmental committee in the Japan Cabinet Secretariat. He worked as several members of EU's committees to make research issues in FP7 and Horizon 2020.
Alexander V. Smirnov
St. Petersburg Institute for Informatics and Automation (Russia)
Context-aware decision support is required in situations taking place in dynamic, rapidly changing, and often unpredictable distributed environments. Such situations can be characterized by highly decentralized up-to-date data sets coming from various resources located in socio-cyberphysical systems. Such systems tightly integrate heterogeneous resources of the physical world and IT (cyber) world together with social networking concepts. This term is tightly related to such terms as Web 4.0 and Internet of Things (IoT). The goals of context-aware decision support are to assess the relevance of information & knowledge to the problem that requires a decision, to timely provide the decision maker with up-to-date information, and to gain insight in seeking and evaluating possible decision alternatives.
The paper addresses theoretical and technological foundations of context-aware decision support in agent-based environments. The theoretical fundamentals are built around ontologies as a widely accepted tool for the semantic modeling of context information. They provide efficient facilities to represent application knowledge, and to make resources of the dynamic environments context-aware and interoperable. The proposed fundamentals are supported by advanced intelligent technologies (ontology management, context management, smart space, cloud computing, decision mining, and user profiling).
The paper summarizes ten year experience of using Smart-M3 (multi-device, multi-vendor, multi-domain) platform for implementation of service-oriented applications based on information sharing by software agents and related to collaborative work, smart logistic, and infomobility. A novel concept of human-computer cloud as an architectural approach to build decision support systems as agent-based cloud systems is also described. The concept serves as a unifying basis for usage of human-based resources and enables their virtualize like “ordinary” computing resources. Particularly, the paper discusses a tourist decision support system integrating machine-driven (GIS, knowledge-based inference, etc.) and human-driven (recommendation systems, expert competence management, etc.) services.
Prof. Alexander V. Smirnov is head of Computer Aided Integrated Systems Laboratory at St.Peterburg Institute for Informatics and Automation of the Russian Academy of Sciences - SPIIRAS (1994). He received his Ph.D from St.Petersburg State University of Electrical Engineering (1984) and Dr.habil. from SPIIRAS (1994), and became a Full Professor in 1998. Also, he is a Head of International Laboratory on Intelligent Technologies for Socio-Cyberphysical Systems, ITMO University, St.Petersburg (from 2014), and a Director of Joint Master Program on Business Informatics between ITMO University and Rostock University (Germany). He has been involved in projects sponsored by Ford, Nokia, US DoD, European Research Programs (Information Society Technologies, Esprit, Eureka/Factory, etc.), and Russian agencies in the areas of distributed intelligent systems, ontology management, intelligent decision support systems, etc. He is a member of technical committees of IEEE SMC TC on Cyber-Physical Cloud Systems, IFAC TC 5.1 on Manufacturing Plant Control; IFIP TC WG5.1 on Global Product Development for the Whole Life-Cycle, and a fellow of the European Academy of Industrial Management.. His current research is in the areas of ontology-driven information integration, corporate knowledge management, context management, operational decision support, socio-cyber-physical systems. He published more than 300 research papers in reviewed international journals and proceedings of international conferences, books, manuals.