What is RoboEarth?
RoboEarth allows robots to:
- Store and Share Information: Robots can use the common representation provided by the RoboEarth language and the scalable storage provided by the RoboEarth database to store and share information. This has the following key advantages:
- Significantly increases the speed of learning by leveraging the experience of other robots. See e.g.: Robots sharing articulation models.
- Allows developers to create general robot task instructions rather than programming individual robots on a case-by-case basis. See e.g., Sharing a common action-recipe to serve drinks with two different robots in different environments.
- Offload Computation: Robots can use the vast computational infrastructure available on the web for computationally heavy tasks including planning, probabilistic inference, and mapping, among many others. See e.g. Cloud-based collaborative mapping with low-cost robots, knowledge processing as a service with KnowRob, and the cloud robotics framework Rapyuta.
- Collaborate: Robots can use the cloud as a common medium to collaborate and achieve a common task. See e.g., Two robots collaboratively performing a serve-a-drink task in a mock hospital room, and Generating and maintaining consistent world state estimates based on object detections by multiple robots using WIRE.
In addition to the cloud-based infrastructure, RoboEarth offers ROS-compatible, robot-unspecific components for high level control of the robot. See software-components for more details.
RoboEarth offers a Cloud Robotics infrastructure, which includes everything needed to close the loop from robot to the cloud and back to the robot. RoboEarth’s World-Wide-Web style database stores knowledge generated by humans – and robots – in a machine-readable format. Data stored in the RoboEarth knowledge base include software components, maps for navigation (e.g., object locations, world models), task knowledge (e.g., action recipes, manipulation strategies), and object recognition models (e.g., images, object models).
The RoboEarth Cloud Engine (also called Rapyuta) makes powerful computation available to robots. It allows robots to offload their heavy computation to secure computing environments in the cloud with minimal configuration. The Cloud Engine’s computing environments provide high bandwidth access to the RoboEarth knowledge repository enabling robots to benefit from the experience of other robots
More in-depth information can be found in RoboEarth – A World Wide Web for Robots (PDF) published in the IEEE Robotics and Automation Magazine and in Rapyuta: The RoboEarth Cloud Engine (PDF) published in the Proceedings of ICRA 2013. You may also want to browse the RoboEarth Blog or subscribe to our newsletter using the link at the bottom of this page.
RoboEarth: Building an Internet for Robots. A TEDx talk by Gajamohan Mohanarajah.