PSPirmin Schoeder

Pirmin Schoeder

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Pirmin Schoeder has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Using Microwave Simulations for the Generation of Radar Data for Gesture and Activity Recognition: Potential and Challenges for Real-World Applications

    by Nicolai Kern, Pirmin Schoeder, Julian Aguilar, Christian Waldschmidt

    In recent years, algorithms have been successfully developed to recognize a wide range of activities and gestures with millimeter-wave radar sensors. Applications range from patient monitoring in health care [1] to contactless gesture control of smart devices [2] and traffic gesture recognition by autonomous vehicles [3] . All these approaches involve machine learning (ML) models that first extract valuable information from the radar data and then use it to make a prediction about the observed human motion. The design of the involved neural networks often requires the acquisition of an application-specific training dataset. Since the acquisition of large amounts of gesture or activity observations is very laborious, typical radar datasets have a few hundred to a few thousand samples per class [4] , [5] , [6] , [7] . The small number of samples per class prevents the use of very deep neural networks with many layers and millions of trainable parameters. If the neural network becomes too powerful for a given dataset size, it will start to simply memorize the data from training and be unable to correctly classify new samples, a problem known as overfitting . The authors of [8] and [9] train a convolutional neural network (CNN) with increasing depth on a small activity dataset and observe severe overfitting as the model becomes too powerful. This prevents the further increase in accuracy that would be expected from deeper neural networks.


  • Open Access

    On Distributed Radar Networks: Signal Model, Analysis, and Signal Processing

    by Vinzenz Janoudi, Pirmin Schoeder, Timo Grebner, Nils Appenrodt, Juergen Dickmann, Christian Waldschmidt

    A key aspect of the imaging capability of radar systems is the angular resolution, which is determined by the aperture size of the antenna array. Therefore technologies such as MIMO and especially radar networks consisting of multiple independent MIMO radar sensors seek to maximize the virtual aperture size. Depending on the range and velocity resolution of the MIMO radar network, multistatic aspects must be accounted for. So far, those multistatic effects were seen as errors, which must be compensated for in order to restore the classical DoA properties of the virtual aperture, described by the narrowband beam pattern. This paper shows that new virtual aperture designs with larger antenna spacings are possible while still preserving the angular ambiguity range of smaller antenna spacings, as long as the multistatic effects of distributed radar networks, namely radar networks whose virtual aperture is large in comparison to the range resolution, are correctly accounted for. The larger antenna element spacing enables larger aperture sizes leading to higher angular resolution. This paper illustrates that the well-known, Fourier Tranformation-based signal processing is unable to exploit this potential of distributed radar networks, and an computationally efficient approximated matched filter is proposed. This article presents a signal model for distributed radar networks, suitable signal processing, and a comparison to the well-known Fourier Transformation-based signal processing for compact radar networks. Both the signal model and the proposed signal processing are verified by measurements with a radar sensor network composed of 2 MIMO radar sensors operating in the automotive frequency range of $76 \,\mathrm{G}\mathrm{Hz}\,\mathrm{to}\, 81 \,\mathrm{G}\mathrm{Hz}$ providing 64 virtual channels with a range resolution of $0.03 \,\mathrm{m}$ . The virtual aperture size of the radar network is ${\sim }0.5 \,\mathrm{m}$ with virtual antenna spacing of twice the wavelength, but the proposed signal processing still allows unambiguous DoA estimation within the full $180 \,\mathrm{^{\circ }}$ range.


  • Open Access

    Virtually Augmented Radar Measurements With Hardware Radar Target Simulators for Machine Learning Applications

    by Nicolai Kern, Pirmin Schoeder, Christian Waldschmidt

    The acquisition of machine learning (ML) datasets by meas-urements for automotive radar data requires many resources and time. On the other hand, the simulation of complex traffic environments with sufficient level-of-detail is challenging, too. In this letter, a middle way is proposed in which real measurements are virtually augmented by reflections obtained from simulation models. The augmented measurements are then replayed with a hardware-based radar target simulator (RTS). This enables the fast creation of application-specific datasets, as well as advanced functionality tests of algorithms at deployment. To demonstrate the efficacy of the virtually augmented radar data, a set of test drives is augmented by virtual pedestrians performing traffic gestures. Then, a classifier trained on the created dataset is demonstrated to achieve a high classification accuracy of 84.0% on real test data.


  • Open Access

    Signal Model for Coherent Processing of Uncoupled and Low Frequency Coupled MIMO Radar Networks

    by Vinzenz Janoudi, Pirmin Schoeder, Timo Grebner, Nils Appenrodt, Juergen Dickmann, Christian Waldschmidt

    MIMO radar networks consisting of multiple independent radar sensors offer the possibility to create large virtual apertures and therefore provide high angular resolution for automotive radar systems. In order to increase the angular resolution, the network must be able to process all data phase coherently. Establishing phase coherency, without distributing the transmitted RF signal to all sensors, poses a significant challenge in the automotive frequency range of $\text{76 GHz} \,\text{to}\, \text{81 GHz}$ . This paper presents a signal model for uncoupled and low frequency coupled radar networks. The requirements for phase coherent processing for uncoupled radar sensors are systematically derived from the signal model. The proposed signal processing methods, which establish coherency, are sub-aperture based. Both the signal model and the proposed signal processing methods are verified by measurements with radar sensor networks composed of 2 and 3 radar sensors, providing 768 and 1728 virtual channels respectively. Measurements verify that phase noise is insignificant in the process of establishing coherency in uncoupled and low frequency coupled radar networks.


  • Detection of Optical Road Markings With Automotive Radar Sensors

    by Timo Grebner, Lizette Lorraine Tovar Torres, Vinzenz Janoudi, Pirmin Schoeder, Christian Waldschmidt

    Accurate environmental representations play a crucial role in trajectory planning for autonomous driving. In addition to localizing road users, obstacles, and road boundaries, the identification of optical road markings is vital for lane recognition. While optical systems like cameras and lidar sensors are commonly employed for this task, they are susceptible to weather conditions. This paper introduces a novel approach that utilizes automotive chirp-sequence radar sensors exclusively for the detection of conventional road markings. This eliminates the need for additional particles or substances to be applied to the road markings, as demonstrated through an indicative analysis based on real-world measurements in public traffic.


  • Probabilistic SAR Processing for High-Resolution Mapping Using Millimeter-Wave Radar Sensors

    by Timo Grebner, Alexander Grathwohl, Pirmin Schoeder, Vinzenz Janoudi, Christian Waldschmidt

    In the field of autonomous driving, highly accurate representations of the environment are essential for trajectory planning as well as for estimating the vehicle's location. Today, this can be achieved with the help of chirp-sequence radar sensors or radar sensor networks. The possibilities for environmental mapping cover simple point clouds, target list based grid maps and raw data based high resolution synthetic aperture radar (SAR) maps. While for target list based grid maps it has already been shown that a probabilistic occupancy grid map has significant advantages over an amplitude-based grid map in terms of robustness and resolution, no probabilistic approaches to SAR processing exist up to now. This paper presents a fundamental approach of processing radar raw data to generate high-resolution SAR images based on probabilities. A probabilistic SAR processing is presented which combines high resolution environmental mapping with amplitude independent target detection. Based on measurements, a qualitative and quantitative comparison between conventional amplitude and phase-based SAR processing, the presented probabilistic SAR processing, and a probabilistic target list-based occupancy grid map is performed. Since the presented algorithm is not limited to the automotive field and chirp-sequence radar sensors, it can be extended to arbitrary SAR applications and radar architectures.


  • Open Access

    Self-Calibration of a Network of Radar Sensors for Autonomous Robots

    by Timo Grebner, Vinzenz Janoudi, Pirmin Schoeder, Christian Waldschmidt

    Radar sensor networks are today widely used in the field of autonomous driving and for generating high-precision images of the environment. The accuracy of the environmental representation depends to a large extent on the accurate knowledge of the sensor's mounting orientation. Both the relative orientation of the sensors to each other and the relative sensor orientation in relation to the vehicle coordinate system are determining factors. For the first time, the orientation estimation of the radar sensors of a network is possible exclusively on the basis of radar target lists without additional localization and orientation devices such as an IMU or GNSS. In this work, two algorithms for determining the orientation of incoherently networked radar sensors with respect to the vehicle coordinate system and with respect to each other are derived and characterized. With the presented algorithms orientation accuracies up to $0.25 \,\mathrm{^{\circ }}$ are achieved. Furthermore, the algorithms do not impose any requirements on the positioning or the orientation of the radar sensors, such as overlapping field of views (FOVs) or the detection of identical targets. The presented algorithms are applicable to arbitrary driving trajectories as well as for point targets and extended targets which enables the use in regular road traffic.


  • A Unified Model of Coherent Direction-of-Arrival Simulation for Radar Target Simulators

    by Pirmin Schoeder, Vinzenz Janoudi, Timo Grebner, Christian Waldschmidt

    In order to simulate highly realistic scenarios for modern radar sensors, like traffic scenarios, radar target simulators require the capability to generate targets in all four radar dimensions, which are range, radial velocity, azimuth and elevation angle. To generate targets with angular information, coherent direction-of-arrival (DoA) simulation allows a highly accurate and flexible angular simulation, at a minimum of required hardware. In this article a unifying general model for coherent DoA simulation with channel knowledge for radar target simulators is derived. It comprises previous models. We present methods which allow the simulation of arbitrary and adjustable DoAs, without any constraints on the radar array geometry or the implemented beamformer. The proposed models and methods are analytically derived, analyzed by simulations and finally verified by measurements. Lastly, a measurement of a 2D-DoA simulation for a radar with twelve channels is conducted, in order to show the general applicability of the concept.


  • Radar-Based Mapping of the Environment: Occupancy Grid-Map Versus SAR

    by Timo Grebner, Pirmin Schoeder, Vinzenz Janoudi, Christian Waldschmidt

    For autonomous driving vehicles, highly accurate representations of the environment are essential for both trajectory planning and self-localization. Different possibilities allow to generate detailed maps of the environment based on chirp-sequence radar sensors for advanced driver assistance systems (ADASs). For the first time, this letter shows a qualitative comparison between synthetic aperture radar (SAR)- and occupancy grid map (OGM)-based environment representation using identical measurement data. The differences of existing signal processing chains as well as a visual measurement-based comparison of the resulting environmental maps is presented.


  • Open Access

    Flexible Direction-of-Arrival Simulation for Automotive Radar Target Simulators

    by Pirmin Schoeder, Vinzenz Janoudi, Benedikt Meinecke, David Werbunat, Christian Waldschmidt

    In order to simulate realistic traffic scenarios, a radar target simulator must be able to generate multiple radar targets with different directions of arrival. The presented concept is able to generate an arbitrary amount of targets with individual directions of arrival for the radar under test. By measuring the radar channel, the novel approach enables target simulators to simulate arbitrary directions of arrival, while minimizing the required hardware. The optimum setup is derived for radars with a uniform linear receive antenna array. The compensation of placement errors for automotive chirp-sequence frequency modulated continuous wave radars is demonstrated. Finally, the calibration for the setup is provided, and the performance of the presented approach is validated.