Final Report Summary - COLLIS.EUS (Soft Collaborative Intelligent Systems)
COLLISEUS aimed to make significant progress in the methods, tools and systems to build multiagent systems (MAS) for complex environments used by humans based on the idea that the time is now ripe to attempt the next big step forward based in the progress in building integrated cognitive systems of the past ten years.
Soft-computing techniques have been successfully applied to analyse complex systems operating in uncertain and unstructured environments. Their ability to develop implicit and explicit models of system behaviour combined with capabilities to represent the state of knowledge of interacting computational entities, has led to a number of approaches that apply these techniques to develop multiagent systems.
By means of the COLLISEUS project, the outstanding researcher in the field of soft computing from SRI International (Palo Alto, California, United States of America (USA)), Dr Enrique Ruspini, joined the European centre to develop innovative research focused in collaborative information systems involving multiple interacting agents. Dr Ruspini investigated new research lines focused in designing, understanding, and implementing this type of systems. The objectives of these studies were, on one hand, robotic and sensor systems incorporating a large number of interacting agents and, on the other, distributed information systems incorporating sophisticated coordination and interaction tools. Soft-computing techniques were applied to the design, analysis, and implementation of multiagent systems including hybrid systems where several human and autonomous agents collected, exchange, and process information to regulate system behaviour. Multiple agent systems are ubiquitous in science, industry, and commerce. The project was based in a multidisciplinary approach that integrated developments stemming from insights from a number of perspectives, notably biology, cognitive science, linguistics, economics, and social sciences.
The innovative methodologies generated in the field of multiagent systems to improve information and communication technology (ICT) models and tools cover a wide range of applications such as manufacturing, control, diagnosis, energy and road traffic management that have leaded to the improvement of business productivity and to the development of new products and services. The flexibility of the methodologies ensures that they are not biased towards a particular type of application and will raise a range of diverse requirements. The scientific knowledge and technological breakthroughs provided by the project will permit to create new systems.
Furthermore, new cross-cutting research lines have aroused in the framework of COLLISEUS, some of them in collaboration with European companies, favoring the transfer of knowledge and the improvement of European industries' innovation capabilities and economical performance.
COLLISEUS was motivated by fundamental issues of knowledge and innovation sectors in Europe and the results generated by its execution will serve as a pathfinder for future innovations and for creating the critical mass that can make a considerable difference for Europe in the long run. The project was based in academic research but has important contributions from industrial partners in order to achieve the long term socio-economical utilisation of the know-how developed by the project.
