.Are you looking for an opportunity to apply Deep Learning to a real-world problem while researching novel representation of graph data? Join Kollmorgen to engage in cutting-edge research, pioneering the application of Graph Neural Networks for predictive traffic modeling in Automated Guided Vehicles, accelerating the deployment of automation in intralogistics and contributing to ground-breaking improvements in user experience. Background An Automated Guided Vehicle (AGV) system is a fleet of mobile robots that automatically transport goods in a network of fixed virtual roads, designed according to the specification of the particular site. This network must have the capacity to handle the intended traffic load without traffic jams, which is verified by running simulations. However, such simulations are time consuming, and since the design process is an iterative one, faster feedback would directly translate to decreased cost in these automation projects. In this master thesis project, you will research how Machine Learning can be used to speed the design process by predicting the consequences of different design choices. Goal of the thesis Your job will be to continue the work of three previous master thesis projects, carried out in 2023 and 2024. The first thesis used Graph Neural Networks to predict the traffic score of an intersection, the second thesis predicted the wait time (due to congestion) associated with each individual road segment, and the third one investigated the generalization capabilities of these models by applying it to more diverse datasets. In this thesis, you will expand the capability of the model to handle more complex scenarios, by developing novel mechanisms to embed traffic rules into the input data structure, i.E. the graph, processed by the Graph Neural Network. Method Construct training datasets by modifying real AGV system layouts and augmenting with synthetic data. Collaborate with domain experts to represent traffic rules in a graph-like data structure. Experiment with deep learning architectures, focusing on Graph Neural Networks. Perform model selection and hyperparameter tuning. Evaluate model robustness and reliability using techniques like K-fold cross-validation. About you Hold a Bachelor Degree in Computer Science, Applied Mathematics or similar; Enrolled in relevant master program such as Algorithms, Engineering Mathematics, Complex Adaptive System or Data Science/AI; Completed courses in Machine Learning and statistics; Had previous work experience as programmer; Had experience of Python, including libraries such as numpy ,pandas, sklearn and pytorch/tensorflow; Experience ofresearch is meritorious