Data-driven positioning in Industry 4.0 and logistics

As a fundamental requirement for many applications in logistics and Industry 4.0, object positioning is an area in which Fraunhofer IIS has not only considerable expertise but also many years of experience. Applications frequently rely on radio-based positioning solutions, which typically measure the transit time of radio signals from mobile objects. To a large extent, the accuracy of the positioning system depends on the optimization of fusion and system parameters in different and sometimes changing environments.

Fraunhofer IIS is therefore working to develop more robust positioning methods. With the help of machine learning, the aim is to calculate positions automatically by using reference measurements as empirical data. The raw data consist of measurements from a positioning system used to train deep neural networks, which can wholly or partially replace existing positioning techniques.

The ADA Lovelace Center is continuing this process of technological development by addressing topics such as fine training in changing environments, active learning to calibrate the model, motion models, and hybrid sensor fusion.