INTeractive RObotics Research Network

INTRO aims to create a new generation of robotic researchers with a broad understanding of the research and technologies needed to build intelligent robots that function in close interaction with humans in unstructured, changing real world conditions. The research will develop the necessary foundations to expand robots into new markets by creating novel systems with cognitive and multi- modal interaction abilities. INTRO offers multidisciplinary training in a joint industrial and academic environment, aiming to provide best-fit robotic researchers with highly specialized knowledge blended with complementary skills and valuable hands-on experience. Despite intensive R&D efforts in robotics, autonomous robots can still not perform reliably in unknown, dynamic, and populated environments. Current robotic systems perform well only when all conditions are known and well defined. They cannot cope with unexpected situations encountered in unstructured, changing real-world conditions. This drawback currently limits the commercial application of robots. To expand robotics applications into real-world environments, the robots must be constructed for a large variety of tasks and be able to adapt continuously to new and changing working conditions. The adaptation to new tasks cannot be achieved by regular end-user programming. Rather, the robot must be delivered with advanced capabilities to learn new tasks and new working conditions from its new user in its new environment. A human may aid the robot in its learning process by showing it how to solve new tasks and how to improve or expand already learned behaviours. This will enable the robot to handle unknown and unpredictable events that are beyond the competence of current autonomous robotic systems. To deal with human actions and interactions, robots must understand human-communication and affect cues; they must detect and respond to the practical, social and affective needs, intentions and demands of the users, the applications and the tasks. A populated environment is inherently non-deterministic from the robot s point of view, and every operation must be conducted at a high cognitive level considering all possible situations. Furthermore, the users themselves may change (the user may get used to the system, the user may become tired, the user's priorities for using a system may change [i.e., speed vs. accuracy], or a different user may start to use the system). Safety is a critical issue that must be realised before a robot enters everyday human populated environments. The robot must avoid hurting any human and should also prevent damage to itself if and when it receives incorrect human advice. To advance robotics into new domains, such as consumer, service, home and entertainment applications, varying forms of interaction between humans and robots are required; it is these interactions under the general term of Interactive Robotics that constitute the overall research theme of the INTRO proposal. The proposed multidisciplinary research project aims to meet these challenges by developing novel modules necessary for such interactive robots. The idea is to combine human flexibility, intelligence and experience with the advantages of the robotic system. This will be achieved by enabling the robot to interact with the human whenever required and to learn from the human if possible and when beneficial, using easy and safe interaction tools. The specific research objectives are to improve robots capabilities by combining human and robot experience and to provide robots with cognitive and multi-modal interaction abilities. These objectives are highly interconnected and require experts from several different disciplines represented by the members of the consortium. Furthermore, they directly address industrial needs. The proposed training has a strong multidisciplinary approach complemented by specialized domain knowledge. Young researchers will work closely with industries, endowing them with insight and understanding of the industrial product life-cycle and valuable hands-on experience of top-level industrial robot development. By blending complementary skills, INTRO will improve the career perspectives of young researchers, in both academic and industrial sectors. This will be achieved through a transnational network of universities and robot companies, with senior researchers from different disciplines (robotics, artificial intelligence, cognitive sciences, human factors) coming from different 'schools-of-thought' (computer sciences, industrial engineering, psychology).