Chupyna B. A., Sokolova N. O., Osadcha O. V.

Oles Honchar Dnipropetrovsk National University


The past decade has seen robots begin to move from factories into household-like environments, folding towels and serving drinks. The demand for these service robots is predicted to grow steadily in the coming decades. But moving from half a century of comfort in structured factory environments to highly unstructured, non-deterministic household environments presents the robotics community with several challenges. Computing power is a key enabler for solving some of these challenges. However, on-board computation entails additional power requirements, which may constrain robot mobility, reduce operating duration, and increase costs. The computational burden of a service robot can be reduced by offloading those tasks that do not have hard real time requirements to a cloud computing infrastructure. These tasks include grasp planning , mapping , and navigation. The rapid increase in mobile data transfer rates makes more and more robotics tasks feasible for execution in the cloud.

RoboEarth is a World Wide Web for robots: a giant network and database repository where robots can share information and learn from each other about their behavior and their environment. Bringing a new meaning to the phrase “experience is the best teacher”, the goal of RoboEarth is to allow 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.

RoboEarth offers a Cloud Robotics infrastructure, which includes everything needed to close the loop from robot to the cloud and back to the robot (an operating system, an execution environment, a database, and a communication server). 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 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.

February 18, 2013 the released of the first public version of the Rapyuta, as well as the framework for applications. The project is created on the principles of Open Source. February 18, 2013 the released of the first public version of the Rapyuta, as well as the framework for applications. The project is created on the principles of Open Source. That allow the project to solve problem of differences between web and robotics applications and develop quickly . Such differences include programming languages, the number of processes (robotics applications contain multiple processes while web applications are typically single processes), and the communication protocols (a request/response based stateless model is sufficient for most web applications, while most robotics applications require servers with stateful protocols to push information asynchronously to the robot).

This technology will make robots smarter, better, faster, and most importantly – cheaper. Which in turn will accelerate the introduction of robots in our everyday lives.