Object-relative mobile robot navigation is essential for a variety of tasks, eg autonomous
critical infrastructure inspection, but requires the capability to extract semantic information …

Notation conventions for rigid transformations are as diverse as they are fundamental to the
field of robotics. A well-defined convention that is practical, consistent and unambiguous is …

This paper presents a new deep learning-based method for the detection of tea box
orientations in shelf images. Due to the lack of data, we had to generate synthetic datasets …