Recent research has demonstrated promising results regarding data-driven dynamic models for target tracking. Wellknown analytic models such as Continuous White Noise Acceleration (CWNA) build on strict assumptions about the behavior of an object of interest, yielding an analytical formulation. In contrast, data-driven models infer information about the target dynamics from a representative dataset via optimization. Consequently, they are specifically tailored to the behavior of the previously observed targets and thus can avoid a model mismatch in case the true motion model is unknown or cannot be easily represented analytically. However, learned models are restricted by the distribution of the underlying training data and consequently fail if this distribution does not match the data distribution of the actual application. This paper aims to combine both analytic and data-driven motion models into a single architecture, hence benefiting from their respective strengths. Furthermore, machine learning capabilities are exploited to simultaneously learn the target velocity and reparameterize the process noise, leading to a more stable convergence. A set of comprehensive experiments analyzes the performance compared to purely data-driven or analytical approaches and an ablation study is performed to identify the effect of individual framework components. The analysis provides valuable insights in the utility of the respective paradigms for potential use-cases and outlines the weaknesses and strengths of the compared methods in such applications.

This research paper investigates the anticipated improvement in emitter localization time simulating a UAV (unmanned aerial vehicle) sensor platform that allows for variable flight altitudes, contrary to maintaining a fixed flight altitude. The study aims to quantify efficiency gain and evaluates whether these gains justify the additional hardware and software complexities involved with variable flight control. The considered UAV sensor platform carries a radio-frequency (RF) direction-finder system. The sensor platform is maneuvered by a controller maximizing the Fisher information to minimize the required mission time until emitter localization. Additionally, a benchmark control strategy further introduced as Loitering is considered, which steers the platform in a circular maneuver around the emitter at constant radius. Simulations are conducted involving various parameters to thoroughly compare the altitude control modes and quantifying the improvements of enabling variable altitude control. The comparison reveals only minor improvements in the scenarios, which initialize the sensor platform at altitudes lower than $50[\mathrm{~m}]$. The effort required to fulfil the requirements for variable height control is discussed, with the conclusion that the effort does not outweigh the effect for UAVs with initial altitudes below $50[\mathrm{~m}]$.

The performance of data fusion and tracking algorithms often depends on parameters that not only describe the sensor system, but can also be task-specific. While for the sensor system tuning these variables is time-consuming and mostly requires expert knowledge, intrinsic parameters of targets under track can even be completely unobservable until the system is deployed. With state-of-the-art sensor systems growing more and more complex, the number of parameters naturally increases, necessitating the automatic optimization of the model variables. In this paper, the parameters of an interacting multiple model (IMM) filter are optimized solely using measurements, thus without necessity for any ground-truth data. The resulting method is evaluated through an ablation study on simulated data, where the trained model manages to match the performance of a filter parametrized with ground-truth values.