Machine Learning & Model Predictive Control for Autonomous Vehicle Motion Control

Institut

Lehrstuhl für Fahrzeugtechnik

Typ

Bachelorarbeit / Semesterarbeit / Masterarbeit /

Inhalt

experimentell / theoretisch /  

Beschreibung

Are you eager to be at the forefront of cutting-edge technology shaping the future of autonomous vehicles? Our team pioneers the development of a revolutionary learning-based, self-adaptive, and robust Model Predictive Controller for trajectory following. Here, you'll engage in groundbreaking projects, developing Machine Learning algorithms to enhance performance and ensure robust control of vehicle dynamics.

This isn't just about applying theoretical knowledge; it's about broadening your skill set, embracing new concepts, and becoming an expert in your field while making tangible real-world impacts with your ideas. Join us and witness your contributions come to life on actual vehicles.

If you're interested in taking on this challenge, don't hesitate to send us an initiative application and we will arrange a call to discuss the topics. Just send me an e-mail with a short motivation, curriculum vitae, and a recent transcript of records. We can't wait to see what you bring to the table.

 

Currently, you can handle one of the following topics in your thesis upon agreement:

• Learning-based & self-adaptive MPC topics:
  • Deep Reinforcement Learning and Bayesian Optimization for MPC parameters
  • Explainable Deep Reinforcement Learning
  • Online learning & parameter estimation for an adaptive prediction model
  • Uncertainty Estimation for Adaptive Stochastic Nonlinear MPC
  • Comparing Stochastic and Robust NMPCs for motion control using a real passenger vehicle as a benchmark
  • Enhancing MPC prediction model with Gaussian Process Regression
• Investigation, modeling and sensitivity analysis of uncertainties and disturbance on the system state in the vehicle context (e.g., crosswind)

Voraussetzungen

• Motivation to familiarize yourself with new topics and to try new ideas
• Ideally previous theoretical knowledge in Model Predictive Control
• Ideally previous experience with Python and Git

Verwendete Technologien

Python, C++, Programming, Autonomous Driving, Machine Learning, Reinforcement Learning, Deep Learning, Model Predictive Control, MPC, Bayesian Optimization, Gaussian Process Regression, Parameter Estimation, Heuristics, motion control, learning

Tags

FTM Studienarbeit, FTM AV, FTM Zarrouki, FTM Informatik, FTM Perception

Möglicher Beginn

sofort

Kontakt

Baha Zarrouki, M.Sc.
Raum: MW3527
Tel.: +49 (89) 289 - 10498
baha.zarroukitum.de

Ausschreibung