Robots gain new function: algorithm automatically recognises sensors and their mathematical modelling
Robots need localisation algorithms to figure out where they are. These algorithms usually work with sensor data, which can be used to calculate their position. For engineers and researchers, figuring out how a sensor is built, what format the sensor data is in, and how the sensor is calibrated on a robot can be quite a challenge. Christian Brommer and his team at the Control of Networked Systems research group at the University of Klagenfurt have developed a new method that eliminates the need for all of this: the algorithm automatically recognises the sensor model and calculates important data for localisation.











