We moved the roboearth stack documentation to roboearth_stack. If you are looking for documentation of the object recording and detection tools, look there.
The goals of RoboEarth are (1) to prove that a networked information repository like RoboEarth greatly speeds up the learning and adaptation process that allows robotic systems to perform complex tasks, and (2) to show that a system connected to such a repository is capable of autonomously carrying out useful tasks that were not explicitly planned for at design time.
The vision of RoboEarth is to create an Internet for robots - a world wide, common knowledge base where robots can share knowledge about objects, environments, and actions with other robots.
Until recently, robots have not been capable of understanding and coping with unstructured environments (like the ones humans work in) because they have relied on knowing in advance the specifics of every possible situation they might encounter. Each response to a contingency has had to be programmed in advance, and systems have had to rebuild their world model from sensor data each time they had to perform a new task.
RoboEarth uses the Internet to create a giant open source network database that can be accessed and continually updated by robots around the world. With knowledge shared on such a vast scale, and with businesses and academics contributing independently on a common language platform, RoboEarth has the potential to provide a powerful feed forward to any robot’s 3D sensing, acting and learning capabilities. RoboEarth aims at allowing robotic systems to benefit from the experience of other robots, paving the way for rapid advances in machine cognition and behaviour, and ultimately, for more subtle and sophisticated human-machine interaction.
For further information, have a look at some of RoboEarth's software components below and visit http://www.roboearth.org.
KnowRob is a knowledge processing system that combines knowledge representation and reasoning methods with techniques for acquiring knowledge and for grounding the knowledge in a physical system. It can serve as a common semantic framework for integrating information from different sources and is used in RoboEarth as local knowledge base on the robot.
Rapyuta: The RoboEarth Cloud Engine
The RoboEarth Cloud Engine is an open source Platform-as-a-Service (Paas) framework designed specifically for robotics applications. It helps robots to offload heavy computation by providing secure customizable computing environments in the cloud. The RoboEarth Cloud Engine’s nick name is “Rapyuta”, after the castle in the sky inhabited by robots featured in the Japanese movie Tenkū no Shiro Rapyuta.
Rapyuta’s computing environments allow robots to easily access the RoboEarth knowledge repository. Furthermore, they are tightly interconnected, paving the way for deployment of robot teams.
The RoboEarth Database is a WWW-style database based on Apache Hadoop. We recommend to use the RoboEarth platform at http://api.roboearth.org, which allows you to participate in a community of users who share data about environments, actions, and objects.
Documentation for the setting up your own instance of a RoboEarth database
RoboEarth Object Model Recording and Object Detection with RoboEarth
This set of ROS packages allow both users and robots to create a point cloud model from an object using a Kinect camera and a marker pattern, to store the resulting model in the RoboEarth knowledge repository, and to later download object models and use them for object detection.
The WIRE stack allows to generate and maintain one consistent world state estimate based on object detections. It solves the data association problem by maintaining multiple hypotheses and facilitates tracking of various object attributes.
Feel free to ask on our mailing list if you encounter problems or need more information.