Intelligent and distributed control for the friendly-interaction with low-cost robots in domestic environments
The aim of this project is the design of an "intelligent control space" which allows the coordination of small and large robots in domestic environments, and that fulfils two fundamental properties for its possible future exploitation or patent: a) to be friendly with the user - any person would be able to install it at his/her house with only a manual - b) it must be scalable - it has to allow the introduction of new domestic robots with only establishing the tasks that the robots can carry out and how they will communicate -. This control space is used to solve four tasks of interest: floor cleaning, care of people who lay on the floor due to having fainted or fallen down, detection and alarm of risk situations, and entertainment.
Through this project we tackle with big research challenges, such as the simultaneous learning of the environment representation and the actions that the robot must carry out as a result of observing the human behaviour. We also have to design strategies that allow the automatic detection of representative situations that require the presence of robots – a room without people that can be tidied up, people sitting in a sofa or children playing capable of being entertained, people that have just entered home and can be welcomed, etc—. This represents an important qualitative leap forward as the low cost robots stop being passive to turn into robots with "initiative". On the other hand, this approach also represents a major advance towards the vision guided robotics, specifically towards the automatic interpretation of human actions and behaviours.
Project
/research/projects/control-intelixente-distribuido-para-a-interaccion-amigable-con-robots-de-custo-reducido-en-ambitos-domesticos
<p>The aim of this project is the design of an "intelligent control space" which allows the coordination of small and large robots in domestic environments, and that fulfils two fundamental properties for its possible future exploitation or patent: a) to be friendly with the user - any person would be able to install it at his/her house with only a manual - b) it must be scalable - it has to allow the introduction of new domestic robots with only establishing the tasks that the robots can carry out and how they will communicate -. This control space is used to solve four tasks of interest: floor cleaning, care of people who lay on the floor due to having fainted or fallen down, detection and alarm of risk situations, and entertainment.</p> <p>Through this project we tackle with big research challenges, such as the simultaneous learning of the environment representation and the actions that the robot must carry out as a result of observing the human behaviour. We also have to design strategies that allow the automatic detection of representative situations that require the presence of robots – a room without people that can be tidied up, people sitting in a sofa or children playing capable of being entertained, people that have just entered home and can be welcomed, etc—. This represents an important qualitative leap forward as the low cost robots stop being passive to turn into robots with "initiative". On the other hand, this approach also represents a major advance towards the vision guided robotics, specifically towards the automatic interpretation of human actions and behaviours.</p> - Roberto Iglesias Rodríguez - Eva Cernadas García
projects_en