Speaker
Description
Pallets are one of the most important load carriers for international supply chains. Yet, continuously tracking activities such as driving, lifting or standing along their life cycle is hardly possible. As part of a preliminary project, it was shown that it is possible to develop a prediction model for pallet activities using data from inertial measurements units mounted on a pallet. A significant challenge in the development of the prediction model is the manual recording and annotation of processes, which significantly restricts the available data. The utilisation of synthetic data derived from physics simulations provides a potential solution to the challenges posed by the scarcity of data and the inability to identify a comprehensive range of processes. To validate this approach, data is recorded in real intralogistics environments and simulation models are created that mimic these real processes. The simulation models are then used to generate synthetic data. To record the real data, a new sensor board was developed, which was adapted for recording in industrial environments. The quality of the synthetic data is then evaluated by comparing it with the recorded data.
