Laurin Ludmann
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Laurin Ludmann has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Jens Neubeck
Forschungsinstitut für Kraftfahrwesen und Fahrzeugmotoren Stuttgart (FKFS), Pfaffenwaldring 12, 70569 Stuttgart, Germany
3 shared publications Andreas Wagner
Institute of Automotive Engineering, University of Stuttgart, Stuttgart, Germany
2 shared publications- Andreas Wagner
Universität Stuttgart
2 shared publications - Chuchu Fan
Massachusetts Institute of Technology
2 shared publications - Jaeyoun Choi
Reliable Autonomous Systems Lab, Massachusetts Institute of Technology, Cambridge, MA, USA
2 shared publications - Akshay Narla
Institute of Industrial Automation and Software Engineering, University of Stuttgart, Stuttgart, Germany
1 shared publication
Latest Publications
- Open Access
A Hybrid Physics-Augmented Neural Network for Dynamic System Modeling with Partially Known Dynamics
This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs—such as long short-term memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear-wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results in this application confirm that hybrid models yield superior performance over strict physical approaches and can implicitly approximate submodel dynamics within a unified, yet modular, architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.
Open AccessA Hybrid Physics-Augmented Neural Network for Dynamic System Modeling with Partially Known Dynamics
This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs—such as long short-term memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear-wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results in this application confirm that hybrid models yield superior performance over strict physical approaches and can implicitly approximate submodel dynamics within a unified, yet modular, architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.
- Open Access
- 8 June 2026
- Published by MDPI AG in Preprints.org
A Hybrid Physics-Augmented Neural Network for Dynamic System Modeling with Partially Known Dynamics
This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs — such as Long Short-Term Memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training, and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results confirm that hybrid models yield superior performance over strict physical approaches and can implicitly learn submodel dynamics within a unified, yet modular architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.
- 8 June 2026
- Published by MDPI AG in Preprints.org
Open AccessA Hybrid Physics-Augmented Neural Network for Dynamic System Modeling with Partially Known Dynamics
This paper introduces Hybrid Physics-Augmented Neural Network (HyPA-Net), a hybrid modeling framework that integrates physics-based linear time-invariant models with artificial neural networks (ANNs) to address dynamic system modeling when only partial physical knowledge is available. The approach leverages the interpretability and robustness of established physical models while using ANNs — such as Long Short-Term Memory architectures—to capture unknown or nonlinear system behaviors. The methodology normalizes state and input variables for compatibility with ANN training, and expands traditional recursive state-space equations for efficient backpropagation over sequences. Vehicle dynamics, specifically using a rear wheel steering test case, validate the proposed framework. Various HyPA-Net configurations are benchmarked against pure physics-based and pure data-driven models, demonstrating improved prediction accuracy and model flexibility. The experimental results confirm that hybrid models yield superior performance over strict physical approaches and can implicitly learn submodel dynamics within a unified, yet modular architecture, opening avenues for applications in domains where partial physics-based knowledge is available but insufficient on its own.
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 94062-94085
Mapping the Software-Defined Vehicle Landscape: Use Cases, Technologies, and Expert Insights
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 94062-94085
Open AccessMapping the Software-Defined Vehicle Landscape: Use Cases, Technologies, and Expert Insights
- 24 December 2024
- Published by Springer Nature
- p. 103-119
Optimization of the Comparability Between Road Testing and the Handling Roadway Test System
- 24 December 2024
- Published by Springer Nature
- p. 103-119
Optimization of the Comparability Between Road Testing and the Handling Roadway Test System
- 30 June 2024
- Published by Springer Nature
- p. 382-393
Detection of Driving Dynamics Anomalies Using Deep Learning
- 30 June 2024
- Published by Springer Nature
- p. 382-393
Detection of Driving Dynamics Anomalies Using Deep Learning