Master thesis (f/m/x): Development of a Motion Cueing Algorithm using MPC and RL

Job Description

Req ID:

4865

Place of work:

Oberpfaffenhofen

Starting date:

ab sofort

Career level:

Student research project and final thesis

Type of employment:

Part time, Full-time

Duration of contract:

6 Monate

Remuneration: Remuneration is in accordance with the Collective Agreement for the Public Sector - Federal Government (TVöD-Bund).

Enter the fascinating world of the German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt e. V.; DLR) and help shape the future through research and innovation! We offer an exciting and inspiring working environment driven by the expertise and curiosity of our 12,000 employees from 100 nations and our unique infrastructure. Together, we develop sustainable technologies and thus contribute to finding solutions to global challenges. Would you like to join us in addressing this major future challenge? Then this is your place!

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

In the Department of Flight Control and Simulation, one of the main research activities is the development of full-motion simulators and the algorithms that control them. Motion cueing algorithms transfer motion from a simulated vehicle, such as an aircraft or car, to the workspace of the motion simulator. Since the platform cannot reproduce the full motion of the simulated vehicle, these algorithms must generate motion cues that preserve the most important dynamic characteristics while remaining within the simulator’s physical limits. The goal of this thesis is to combine a Model Predictive Control (MPC) approach with reinforcement learning to improve the quality of the generated motion cues.

Your tasks

• Familiarize yourself with the motion simulator setup, including mechanical design, system dynamics, and control architecture

• Analyze the existing MPC-based motion cueing algorithm and its integrated vestibular perception model

• Develop and implement a reinforcement learning approach to improve the MPC-based motion cueing algorithm

• Evaluate the performance of the proposed method in simulation

• Optional: Deploy and test the developed algorithm on the real motion simulator

Your profile

• Master’s student in robotics, mechanical engineering, aerospace engineering, control engineering, or a related field

• Background in control systems, robotics, or dynamic systems

• Programming experience in Python (experience with optimization or machine learning frameworks is beneficial)

• Interest in reinforcement learning, model predictive control, and motion simulation

• Independent and structured working style

We offer

DLR stands for diversity, appreciation and equality for all people. We promote independent work and the individual development of our employees both personally and professionally. To this end, we offer numerous training and development opportunities. Equal opportunities are of particular importance to us, which is why we want to increase the proportion of women in science and management in particular. Applicants with severe disabilities will be given preference if they are qualified.

We offer DLR stands for diversity, appreciation and equality for all people. We promote independent work and the individual development of our employees both personally and professionally. To this end, we offer numerous training and development opportunities. Equal opportunities are of particular importance to us, which is why we want to increase the proportion of women in science and management in particular. Applicants with severe disabilities will be given preference if they are qualified.

We look forward to getting to know you!

If you have any questions about this position (Vacancy-ID 4865) please contact:

Thomas Bernhofer Mail: [email protected]