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

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