Consistent World Models for Cooperating Robots: Separating Logical Relationships, Sensor Interpretation and Estimation

Andreas Schierl, Andreas Angerer, Alwin Hoffmann and Wolfgang Reif

When working with multiple independent mobile robots, each has a different knowledge about its environment, based on its available sensors. This paper proposes an approach that allows working with these different views by independently modeling the common logical relationships between the elements in the scene and the meaning of device-specific sensor data. Using these models, for each robot an estimation process can automatically be derived that combines and processes the available information to fill in the unknown geometric relationships between the elements, while reacting to changes in the logical relationships. The proposed approach facilitates the consistent coordination of the robots through an application that works on a common world model, while for execution each robot uses its available data and estimations. The approach is demonstrated in a case study of two cooperating mobile robots that pick up an object and hand it over while passing each other.
published 10.04.2017 2017 First IEEE International Conference on Robotic Computing (IRC) DOI: 10.1109/IRC.2017.62


For questions regarding the publication, please contact!