Welcome to the Institute of Flight Systems. Our work focuses on the interaction between aircraft configuration, pilots and modern flight system technology. From flight dynamics to unmanned aerial vehicles, from simulation to real flight tests - we analyse, test and develop innovations that will shape the flying of the future.
What to expect
The research project UAdapt develops novel technologies for high-performance and adaptive unmanned aircraft systems. One of its main objectives is the development of morphing wing technologies that continuously adapt the wing geometry to changing flight conditions. This enables improvements in flight performance, efficiency, and operational safety. To fully exploit the potential of these technologies, innovative AI-augmented flight control methods are being developed and integrated into real flight test campaigns.
Within this internship or thesis, you will integrate an existing roll attitude controller into a high-performance companion computer and incorporate it into the aircraft's existing flight control architecture. The implementation is based on a ROS software framework and will serve as the foundation for future flight experiments with the demonstrator aircraft. You will gain practical experience in modern flight control, embedded systems, and the development of software for safety-critical aerospace applications.
Your tasks
- Implement an existing roll attitude controller in C++ within a ROS-based software architecture and port it to a companion computer
- Integrate the controller into the existing flight control system by implementing suitable interfaces between the companion computer and the autopilot
- Perform Software-in-the-Loop (SiL) and Hardware-in-the-Loop (HiL) testing
- Validate the controller's performance in simulation and during flight test preparation
- Document and present the achieved results
- Optional: Demonstrate the controller during flight tests
Your profile
- Current enrollment in a Master’s program in Computer Science, Control Engineering or a related field
- Solid background in reinforcement learning, ideally policy gradient methods
- Good understanding of control engineering and flight dynamics
- Experience with TensorFlow, PyTorch for numerical optimization, neural networks and deep learning
- Strong programming skills, particularly in Python or C++
We look forward to getting to know you!
If you have any questions about this position (Vacancy-ID 5653) please contact:
Lennart Kracke
Tel.: +49 531 295 1022
