We are Zeekr Technology Europe. Powered by engineers and creative minds from all over the world. Located in Gothenburg, Sweden, one of the leading mobility innovation grounds worldwide. Established in 2013 as CEVT and began with the mission to create a revolutionary modular vehicle architecture, CMA. As of 2024, CEVT is now Zeekr Technology Europe, signaling our belonging within Zeekr. Delivering intelligent, sustainable, and user centric technology and software for tomorrow's electric mobility today.

Project description:

Learning-Enhanced NMPC: A Residual-Model and Reinforcement Learning Warm-Start Framework

Ready to build the next generation of smart controllers? Model Predictive Control is powerful but can stumble on model mismatch and heavy compute. In this thesis, you’ll create a learning-in-the-loop Nonlinear MPC where Reinforcement Learning (RL) learns residual dynamics (closing the model gap) and warm-starts the solver (cutting iterations and latency). You’ll prove it first on a nonlinear cascaded two-tank benchmark with overflow, then scale the framework to a Battery-Electric Vehicle thermal management case.

You’ll sit at the frontier of safe learning-in-the-loop control—bringing RL benefits without giving up MPC’s constraint handling. Recent literature signals strong potential but leaves room for unified methods and deployment-focused benchmarks.

Key focus areas: Residual learning for mismatch, Reinforcement Learning warm-starts,

Research goals:

• Build a nominal NMPC and add a learned residual model (GP/NN) to reduce mismatch.
• Train a policy to initialize the NMPC solution sequence to reduce iterations/solve time.
• Ensure constraint satisfaction via MPC.
• Validate on tanks; transfer the framework to BEV thermal scenarios.

Key tasks:

• Implement NMPC (CasADi/ACADOS/MATLAB) on tanks.
• Add residual learning (GP vs. small NN).
• Train a warm-start policy (imitation/RL)
• Port the framework into a simplified BEV thermal mode.
• Report metrics: no-residual vs. residual; no-warm-start vs. warm-start; uncertainty-aware tightening vs. none.

Your skills and background

• Ongoing MSc in Systems, Controls and Mechatronics or Mobility engineering or Data science and AI or Computer science.
• Solid understanding of optimization & control (MPC), Python or MATLAB.

Why you should join Zeekr Tech Eu

We are engineers, developers, and innovators from around the world. Joined together by entrepreneurship, our unique blend of global culture, and a belief in a smarter more sustainable future. At Zeekr Tech Eu we fast-track innovation and transform ideas into pioneering technology solutions, doing your master thesis here is no different. We are convinced that a thesis project is a major contribution to our innovation capabilities and long-term development. You'll have a great opportunity to use your skills and creativity to push the boundaries of what´s possible.

What happens when you apply
If this sounds interesting and you match the requirements, please don't hesitate to submit your application with a CV and cover letter. Shortlisted candidates will be contacted for an interview to further discuss the project's details and expectations. 

This thesis project is intended for 2 students

Supervisor: Prashant Lokur, PhD Student, prashant.lokur@zeekrtech.eu, please contact for more information about the project

Starting date: January 2026

Last application date: 2025-10-28

Apply today. We will perform ongoing selection during the application period. We look forward to hearing from you!

Please note that due to GDPR regulations, we can only accept applications sent through the recruitment system, not via email or other channels.