Towards a Dataset of Realistic 3D Intralogistics Scenes for AI Applications

Realistic data is the crucial basis for the development and operation of artificial intelligence (AI) applications. In intralogistics many applications require realistic 3D representations of the material flow systems as a basis. Capturing real world 3D data or building synthetic 3D scenes by hand is costly. In order to generate realistic scenes, a reference dataset of realistic intralogistics systems is required. This paper shows motivating use cases for a 3D dataset of intralogistics scenes and works out an approach to capture such a dataset.