The RoboEarth project was initiated by a multi-disciplinary partnership of robotics researchers from academia and industry. Their goals:
– to prove that connection to a networked information repository greatly speeds up the learning and adaptation process that allows robotic systems to perform complex tasks, and
– to show that a system connected to such a repository will be capable of autonomously carrying out useful tasks that were not explicitly planned for at design time.
In December 2009, the group received four-year funding from the European Commission’s Cognitive Systems and Robotics Initiative to develop RoboEarth’s open-source network database platform and develop a series of demonstrators to prove the concept.
The demonstrators include using the RoboEarth platform to:
– create and execute action recipes
– integrate localization and mapping
– perform 3D sensing
– learning control
– track objects dynamically
– mine data from RoboEarth past data
The hope is that, with a proof of concept in place, the RoboEarth database can be used as a launch pad for further research and development, leading eventually to standardization, common language protocols and a more modular design of cloud robotics systems.