2002

Funding: European Commission (IST 2001-34304)

Partners: Association of Research and Industrial Co-operation of Andalucia (66), Spain; GMV, Spain; LAAS-CNRS (17), France; Technische Universität Berlin, Germany; University of Coimbra, Portugal; University of Linköping, Sweden; Helivision, Spain.

Duration: 1 May 2002 – 31 July 2005

Description: COMETS designed and implemented a distributed control system for cooperative detection and monitoring using heterogeneous Unmanned Aerial Vehicles (UAVs): both helicopters and airships are included in the system. In order to achieve this general objective a new control architecture has been designed and implemented, new control techniques have been developed, and distributed sensing techniques have been integrated with real-time image processing capabilities. In order to test and validate these concepts and technologies, COMETS has been demonstrated in forest fire detection, confirmation, localisation and monitoring. This is a very challenging mission in which the cooperation of the UAVs is very valuable due to the requirements on the required coverage, redundancies and flexibility when comparing with the use of a single UAV with long endurance flight and important on-board capabilities. COMETS has been the first project implementing the coordination of heterogeneous unmanned aerial vehicles, such as autonomous helicopters and airships, for civil applications in Europe

URL: http://grvc.us.es/comets

Funding: European Commission (IST-FET 2001-35282)

Partners: University of Sunderland, United Kingdom; Medical Research Council, United Kingdom; University of Parma, Italy; INRIA Lorraine, France; University of Ulm, Germany.

Duration: 1 June 2002 – 31 October 2005

Description: Experiments in neuroscience have indicated that a biological and neuroscience-oriented approach for multimodal processing will lead to new life-like perception action systems. In particular, concepts from mirror neurons suggest that own actions, observed actions and language are very much interrelated since the same mirror neurons fire at the same time based on experiments with monkeys and humans. This project MirrorBot develops and studies emerging embodied representations based on mirror neurons. We develop new techniques including cell assemblies, associative neural networks, and Hebbian-type learning in order to associate vision, language and motor concepts. We develop biomimetic multimodal learning and language instruction in a robot to investigate the task of searching for objects.

URL: http://www.his.sunderland.ac.uk/mirrorbot