KEYNOTE SPEAKERS LIST
Luís Paulo Reis, University of Minho / LIACC, Portugal
Title: Multi-Robot Intelligence: Flexible Strategy for Robotic Teams
Anthony G. Cohn, University of Leeds, U.K.
Title: Learning about Activities and Objects from Video
Wolfgang Wahlster, German Research Center for AI, Germany
Title: Towards Software-Defined Networked Cars as Social Agents
Frank Dignum, Utrecht University, The Netherlands
Title: Agents for Serious Gaming; Challenges and Opportunities
Joaquim Filipe, Polytechnic Institute of Setúbal / INSTICC, Portugal
Title: Organisation Modelling with Intelligent Multi-Agent Systems
|
Luís Paulo Reis University of Minho / LIACC Portugal |
Brief Bio
Luís Paulo Reis is an Associate Professor at the University of Minho and a member of the Directive Board of the Artificial Intelligence and Computer Science Lab, Portugal. He received his Electrical Engineering and MSc degrees from the University of Porto in 1993 and 1995, and a PhD in Artificial Intelligence at the same University in 2003. During the last years he taught Artificial Intelligence, Intelligent Robotics, Simulation and Modeling, Planning and Scheduling, Algorithms and Data Structures and Logic Programming courses, mostly at the PhD level. His research interests include Intelligent Robotics, Artificial Intelligence, Multiagent Systems (MAS), Coordination in MAS and Intelligent Simulation. He is one of the team leaders of the FC Portugal robotic soccer team/project. In this project he developed pioneering research work regarding the creation of generic methodologies for coordinating multi-robot teams, applicable to any type of team and application domain. These methodologies enabled FC Portugal to be three times World Champion and six times European Champion in RoboCup (simulation 2d, simulation 3d and rescue competitions). He is the author of more than 200 publications in international conferences and journals and has supervised 7 PhD theses and more than 70 MSc thesis to completion and is currently supervising 15 PhD theses.
Abstract
RoboCup is a worldwide initiative, that aims at fostering artificial intelligence and robotics research. This domain is organized around several Leagues, with different characteristics, and distinct robotic teams but where multi-agent coordination and strategic planning are two of the major research topics. However, innovations in these areas are often developed and applied to only one domain and a single RoboCup league, without proper generalization. This talk presents high-level coordination methodologies that may be applied to create flexible multi-robot teams capable of performing complex tasks in dynamic environments. The methodologies described include flexible formations (situation based strategic positioning), dynamic role and positioning exchange, flexible setplays (freely-definable, flexible and multi-step plans) and the concept of strategy (combining tactics, situations, formations, roles and setplays).
The application of these methodologies to different RoboCup leagues (such as the simulation 2d, simulation 3d, rescue, middle size and standard platform league) is also described along with the very good results achieved in RoboCup competitions by our teams.
|
Anthony G. Cohn University of Leeds U.K. |
Brief Bio
Tony Cohn holds a Personal Chair at the University of Leeds, where he is Professor of Automated Reasoning. He is presently Director of the Institute for Artificial Intelligence and Biological Systems. He leads a research group working on Knowledge Representation and Reasoning with a particular focus on qualitative spatial/spatio-temporal reasoning, the best known being the well cited Region Connection Calculus (RCC). His current research interests range from theoretical work on spatial calculi and spatial ontologies, to cognitive vision, modelling spatial information in the hippocampus, and detecting buried underground assets (e.g. utilities and archaeological residues) using a variety of geo-located sensors. He has been Chairman/President of SSAISB, ECCAI, KR inc, the IJCAI Board of Trustees and is presently Editor-in-Chief of the AAAI Press, Spatial Cognition and Computation, and the Artificial Intelligence journal. He was elected a founding Fellow of ECCAI, and is also a Fellow of AAAI, AISB, the BCS, and the IET.
Abstract
In this talk I will present ongoing work at Leeds on building models of video activity. I will present techniques, both supervised and unsupervised, for learning the spatio-temporal structure of tasks and events from video or other sensor data, particularly in the case of scenarios with concurrent activities. In both cases, the representation will exploit qualititive spatio-temporal relations. A novel method for robustly transforming video data to qualitative relations will be presented. For supervised learning I will show how the supervisory burden can be reduced using what we term "deictic supervision", whilst in the unsupervised case I will present a method for learning the most likely interpretation of the training data. I will also show how objects can be "functionally categorised" according to their spatio-temporal behaviour and how the use of type information can help in the learning process, especially in the presence of noise.
|
Wolfgang Wahlster German Research Center for AI Germany |
Brief Bio
Professor Wolfgang Wahlster is the Director and CEO of the German Research Center for Artificial Intelligence (DFKI) and a Professor of Computer Science. DFKI is the world’s largest contract research center with more than 800 scientists, working for its industrial shareholders including BMW, Daimler, Deutsche Telekom, John Deere, Intel, SAP, EADS and DHL. More than 60 hightech spin-off companies have been founded by DFKI.. Professor Wahlster10has published more than 200 technical papers and 10 books on mobile and multimodal user interfaces, instrumented environments, the semantic web, the internet of things and the internet of services. He is an AAAI Fellow (since 1993), an ECCAI Fellow (since 1999), and a GI Fellow (since 2004). In 2001, the President of Germany presented the German Future Prize to Professor Wahlster for his work on language technology and intelligent user interfaces, the highest scientific award in Germany. He was the first German computer scientist elected Foreign Member of the Royal Swedish Academy of Sciences, Stockholm 2003. In 2004, he was elected Full Member of the German National Academy of Sciences Leopoldina, that was founded in 1652. In 2006, he has been awarded the Federal Cross of Merit, First Class of Germany. He has also been appointed member of the Research Union "Business - Science" as chief advisor for ICT research of the German government and served as a partner for innovation of Chancellor Dr. Merkel. Since 2009 he is a member of the Executive Steering Board of the EIT ICT Labs of the European Institute of Innovation and Technology. In addition, Dr. Wahlster serves on the Executive Board of the International Computer Science Institute at UC Berkeley. He is in the editor of Springer’s LNAI series and on the editorial board of various top international journals like CACM.
Abstract
Intelligent Car2X technologies and networked cyber-physical systems in digital cars create intelligent transportation environments based on software-defined cars that provide tailored services to their users. Future digital cars serve not only as mobile sensors, mobile internet nodes and mobile web servers but also as social agents that collaborate with other cars and drivers for more safety, better energy efficiency, intelligent connectivity and advanced infotainment. We show how software-defined cars can be customized by downloading apps from app stores for digital vehicles. We present a new generation of intelligent car assistants that provide a broad range of situation-aware services from local danger warnings, intelligent intersection and traffic light management to persuasive eco-driving coaching. We will show how a digital black box of the car provides a detailed semantic diary of the car that provides long-term context information. The smart key of our test car can store the shopping list of the driver and can be used for NFC payment in the supermarket. The in-car sensors detect missing shopping items and plan the route accordingly. The car monitors the temperature and the air-conditioning when frozen products are being carried. We will illustrate our approach with various video clips from DFKI’s instrumented BMW and Daimler test vehicles. Finally, we will discuss our current work based on always-on, all-electric and all-IP cars that provide an emotional experience and advanced social network behavior.
|
Frank Dignum Utrecht University The Netherlands |
Brief Bio
Frank Dignum is associate professor of Computer Science at Utrecht University. He is currently also honorary senior research fellow at the University of Melbourne. He leads research in adaptive interactive systems. The research concerns the use of agent technology for (serious) games and simulations, with the aim of making the games and simulations more flexible and adaptive to the user. He has been the technical coordinator of 2 EU projects. He is part of the European network of excellence GaLA. He has obtained numerous national and international grants leading to around 30 researchers working (or having worked) on his grants. He is the initiator and organizer of the international workshop on Agents for Games and Simulations. Besides this workshop he has organized many other agent related workshops and was local organizer of the main agent conference
(AAMAS) in 2005. He is area chair of IJCAI 2011 and workshop chair of AAMAS 2011. He is in the (senior) program committee of many workshops and conferences. He has written over 250 papers in international journals and conferences.
Abstract
In order to create intelligent serious games we need to create a gaming environment that allows and supports intelligent behavior. We need to develop technology for generating adaptive and intelligent game flow, for creating NPC's that behave intelligently within an environment, for interacting intelligently with users, and for understanding user interaction. It seems intuitive to use agent technology for implementing these elements. Although the agent theory contains many interesting ideas it appears that more is needed to put them to practice in serious games. In this presentation I will talk about the opportunities and challenges for agents in serious gaming.
|
Joaquim Filipe Polytechnic Institute of Setúbal / INSTICC Portugal |
Brief Bio
Joaquim B L Filipe is currently a Coordinator Professor and Head of the Department of Systems and Informatics of the School of Technology of the Polytechnic Institute of Setúbal (EST-Setúbal), Portugal. He got his Ph.D. at the School of Computing of the Staffordshire University, U.K, in 2000.
His main areas of research involve Artificial Intelligence and Multi-Agent System theory and applications to different domains, with an emphasis on social issues in activity coordination, especially in organizational modeling and simulation, where he has been actively involved in several R&D projects, including national and international programs. He represented EST-Setúbal in several European projects. He has over 100 publications including papers in conferences and journals, edited books and conference proceedings. He started several conference series, sponsored by INSTICC and technically co-sponsored or in cooperation with major International Associations.
Abstract
Available soon.
