Towards an architecture for semiautonomous robot telecontrol systems

The design and development of a computational system to support robot–operator collaboration is a challenging task, not only because of the overall system complexity, but furthermore because of the involvement of different technical and scientific disciplines, namely, Software Engineering, Psychology and Artificial Intelligence, among others. In our opinion the approach generally used to face this type of project is based on system architectures inherited from the development of autonomous robots and therefore fails to incorporate explicitly the role of the operator, i.e. these architectures lack a view that help the operator to see him/herself as an integral part of the system. The goal of this paper is to provide a human-centered paradigm that makes it possible to create this kind of view of the system architecture. This architectural description includes the definition of the role of operator and autonomous behaviour of the robot, it identifies the shared knowledge, and it helps the operator to see the robot as an intentional being as himself/herself.