The poster will present a project idea that uses multi-agent paradigm in management of multi-robot systems for applications in service robotics domain including domestic, agriculture and public security services. The main role of agents at the management level is to represent robotic systems (physical agents). This approach enables to increase effectiveness of multi robot system management through modelling of future operation scenarios, more efficient and higher level interaction among heterogeneous physical robots as well as higher usability from end-user view point.
The communication presentations (keynote talks, facilitated break-out sessions, posters) will be continuously in May and June.
Agris Nikitenko is assistant professor at Riga Technical University (Latvia).
The research interests of M. Nikitenko include Intelligent agents, Multi-agent systems, Agent-oriented software engineering, Intelligent tutoring systems, Ontology-based software systems, Autonomous software and robotic systems, Machine learning.
Alessio Lomuscio is Professor at Imperial College London (United Kingdom).
The research interests of Prof. Lomuscio concern the logic-based specification and verification of autonomous systems; in particular symbolic verification of multi-agent systems via model-checking (including abstraction techniques, parametric verification, BDD and SAT-based techniques), application of verification methodologies to web-services (including infinite-state artifact-centric systems, autonomous vehicles and security protocols), development and study of modal formalisms (including temporal, epistemic, doxastic, deontic logics and ATL) for the principled specification of multi-agent systems.
To be accepted at societal level, adaptive and autonomous systems need certification. Verification and validation techniques can help to provide reassurances on these systems and have them certified. Traditional techniques focus on reactive systems and cannot be readily applied to adaptive systems in uncertain environments. We need to develop urgently sophisticated verification technology to be able to provide support for validation of adaptive systems. Without guarantees on the behaviours generated by adaptive machines, adaptive systems risk not being adopted in society.
Alois Ferscha is Professor and Head of the Institute for Pervasive Computing at the Johannes Kepler University in Linz (Austria).
The research interests of Prof. Ferscha include networked embedded systems and architectures; cooperative embedded systems; development of embedded systems software; awareness, attention, interaction; parallel and distributed (interactive) simulation.
Modern ICT (Information and Communication Technology) has developed a vision where the “computer” is no longer associated with the concept of a single device or a network of devices, but rather the entirety of situated services originating in a digital world, which are perceived through the physical world. It is observed that services with explicit user input and output are becoming to be replaced by a computing landscape sensing the physical world via a huge variety of sensors, and controlling it via a plethora of actuators. The nature and appearance of computing devices is changing to be hidden in the fabric of everyday life, invisibly networked, and omnipresent, with applica- tions greatly being based on the notions of context and knowledge. Interaction with such globe spanning, modern ICT systems will pre- sumably be more implicit, at the periphery of human attention, rather than explicit, i.e. at the focus of human attention.
Socio-inspired ICT assumes that future, globe scale ICT systems should be viewed as social systems. Such a view challenges research to identify and formalize the principles of interaction and adaptation in social systems, so as to be able to ground future ICT systems on those principles. This position paper therefore is concerned with the intersection of social behaviour and modern ICT, creating or recreating social conventions and social contexts through the use of pervasive, globespanning, omnipresent and participative ICT.
Ann Nowé is professor both in the Computer Science Department of the faculty of Sciences as in the Computer Science group of the Engineering Faculty at the "Vrije Universiteit Brussel".
The research interests of Prof. Nowé comprise Computational Biology, Evolutionary Linguistics, Learning in Multi-Agent Systems, Machine learning for Data mining, and Preference handling.
The rise of “smart” devices comes with a growing need for autonomous controllers that can dynamically interact with humans and adapt to specific demands and preferences of end users. To satisfy these requirements, a number of key challenges have to be overcome, including: recognizing user intentions, adapting to direct and indirect user feedback and continuing the learning process over the entire lifetime of the device. We believe that reinforcement learning, or learning through interactions with the environment , is a key paradigm for the development of devices that meet these needs. The lab currently participates in national projects where some of these aspects are partially addressed. A key element in our approach is that the learning is organised such that the user is not hindered by the learning process. In the future we envision to address preference learning across applications, such that learning can happen more efficiently.
|CHIST-ERA Conference 2013 - Ann Nowé.pdf||1.83 MB|
Charalampos Tampitsikas is a PhD student at the Lugano University in Switzerland.
The research interests of Mr. Tampitsikas include Normative Systems Artificial Institutions Semantic Web Logic Programming Multi-Agent Systems in Energy and e-Health.
A Complex Environment is a system of interacting entities, where its global dynamics and organization are obtained through a non-linear aggregation of the local behaviors of its components. The proactive entities of a Complex Environment can be modeled as autonomous agents capable of learning and adapting their behavior to the requirements of the environment dynamics. Multi-agent systems (MAS), study how these agents can interact and coordinate in an intelligent, flexible and efficient way. Thus, in MASs, it is important to introduce high level agent communication languages in order to ensure that the agents fulfill the goals of their human designers.
Danny Weyns is Professor at the Department of Computer Science of Linnaeus University, Sweden.
The research interest of Prof. Weyns is in software engineering of decentralized self-adaptive systems.
The upcoming generation of socio-technical computing systems, such as intelligent traffic management and networked smart homes, are inherently decentralized systems that have to operate under various uncertainties, e.g., changing user needs, parts that attach and detach at will, and unpredictable availability of resources. Engineering these systems pose severe engineering challenges. From a technical viewpoint these systems should be able to adapt themselves dynamically to changes in a decentralized manner, while assuring service provision. From a methodological viewpoint, engineering these systems requires co-design across the technology stack (from business processes, to architecture and programming, down to hardware) and co-design across disciplines (incl. expertise in technology, sociology, economics, etc.). Providing sustainable solutions in face of uncertainty calls for agility@runtime, where system evolution becomes an interactive runtime process between adaptive computing systems and stakeholders.
|CHIST-ERA Conference 2013 - Danny Weyns & Sabri Pllana.pdf||2.21 MB|
Dimitrios Pezaros is the SICSA Next Generation Internet (NGI) Lecturer at the Embedded, Networked and Distributed Systems (ENDS) Group in the School of Computing Science, University of Glasgow (United Kingdom).
The research interests of Dr. Pezaros lie in Cloud/DataCentre Computing Optimisation and Control, Network Measurement, Control and Management, Network Resilience, QoS/QoE of Multimedia Network Protocols, Home Network Management. Network Traffic Modelling and Anomaly Detection.
The unification of diverse commodity and mission-critical services and data over centralised networked environments makes security of the infrastructure paramount. Current security solutions are either bespoke, don’t scale or operate over long timescales. Future infrastructures will need to offer system security as an emergent native property that will cover diverse service requirements including Big Data under a single, adaptive architecture. Latest advances on programmable network architectures and hardware-accelerated custom compute can be exploited to facilitate situation-aware, system-wide security, embracing real-time anomaly and intrusion detection and remediation for resilient mission-critical, unified ICT infrastructures
Esra Erdem is Associate Professor, Computer Science and Engineering, Sabanci University (Turkey).
The research interests of Prof. Erdem include artificial intelligence. In particular, the mathematical foundations of Knowledge Representation and Reasoning and Cognitive Robotics, and their applications.
As the robotics technology makes its transition from repetitive tasks in highly-structured industrial settings to loosely defined tasks in unstructured human environments, substantial new challenges are encountered placing high demands on the robots' intelligence and autonomy. For example, to deploy robotic assistants in our society, they are expected to robustly deal with high complexity and wide variability of their surroundings to perform typical everyday tasks without sacrificing safety. Knowledge representation and automated reasoning methods help endowing robotic systems with high-level cognitive capabilities, towards adaptive and autonomous systems in real world complex environments, such as cognitive factories, service robotics and rehabilitation robotics.
- 1 of 3
- next ›