Knowledge-Exchange between Robots

The purpose of the RoboEarth project is to create a giant network through which robots and their programmers can easily share information about actions and the world. Similar to what the World Wide Web has done for humans, RoboEarth will enable robotic systems to benefit from the experience of other robots in a way that can be easily translated to their own case. Data stored in RoboEarth include software components, environment maps, task knowledge, and object recognition models. The network will provide a key infrastructure for advancing machine cognition and behavior incrementally on a collective level. In addition the RoboEarth Cloud Engine will make powerful computation available to robots.

Our role in the RoboEarth consortium is to investigate knowledge representation and mechanisms for uploading, exchanging and applying action recipes. For this purpose we build upon our Cognitive Robot Abstract Machine (CRAM) and Knowledge Processing for Autonomous Robots (KnowRob) projects.

For more information and news, visit



This project has received funding from the European Union Seventh Framework Programme FP7/2007-2013 under grant agreement number 248942 RoboEarth.

Prof. Dr. hc. Michael Beetz PhD
Head of Institute

Contact via
Andrea Cowley
assistant to Prof. Beetz

Memberships and associations: