Thesis - Uncertainty-Aware ML for Vehicle Dynamics

We are Geely Technology Europe. A unified European R&D centre within Geely Auto Group, where world-class engineers, developers and innovators push the boundaries of intelligent mobility. Our mission is to shape the next generation of vehicle architectures, digital technologies and intelligent systems for global markets. We integrate European customer and regulatory requirements early in the development process and support multiple brands within the Geely portfolio, including Zeekr, Lynk & Co and Geely. With nearly two decades of engineering experience in Europe, we continue to build smart, sustainable and user‑centric mobility solutions.

Project Description:

Automated driving and driver-assistance functions need to know how much performance the vehicle has left in each situation, its capability envelope. Planning and control algorithms usually rely on simplified models and fixed limits, which can be either too optimistic or too conservative. High-fidelity, physics-based simulation and reachability analysis capture these limits accurately but are far too computationally expensive to run on board. This is an open problem at the intersection of machine learning, simulation and control, how to learn fast and reliable models from expensive simulations, quantify their uncertainty, and adapt them to real-world data.

Scope:

The thesis takes the vehicle's performance limits from high-fidelity simulation to a real-time, self-adapting, data-driven model ready for assisted and automated-driving functions.

• Feature and sensitivity analysis: identify which vehicle, road and actuator variables drive the limits.

• Simulation-based data generation: design efficient sampling strategies, such as design of experiments or active learning, to build training data from high-fidelity models.

• Machine Learning-based modelling and uncertainty quantification: learn fast data-driven models of the limits and quantify how confident they are.

• Online learning and adaptation: update the model from real vehicle data so it tracks changes over time and bridges the sim-to-real gap.

• Safe, real-time deployment: conservative predictions, out-of-distribution detection and embedded implementation.

• Integration and validation: validating the prediction as part of a use case in a simulation environment and/or on the vehicle.

Expected Outcomes

The thesis is expected to demonstrate that a high-fidelity capability envelope can be made deployable, adaptive and useful for assisted and automated-driving functions, with following deliverables

• A quantified comparison between conventional vehicle limits and a high-fidelity capability envelope.

• A method for turning high-fidelity envelopes into a real-time, uncertainty-aware prediction.

• An approach for adapting the envelope online so it stays consistent with the real vehicle.

• A verified and validated prototype, with results from simulation and, where possible, vehicle tests.

• A master's thesis report, with the aim of a scientific publication.

Your skills and background

• Ongoing Master’s degree in Data Science, Machine Learning, Complex Adaptive Systems, Vehicle Engineering, Systems and Control, or a related field

• Strong background in machine learning, including Probabilistic or Bayesian methods and uncertainty quantification

• Experience with machine learning for time series, dynamical systems or surrogate modelling

• Experience with machine learning frameworks (e.g. PyTorch, TensorFlow,.)

• Knowledge in control systems, optimization, vehicle dynamics or applied physics

• Strong programming skills in Python, MATLAB/Simulink and C/C++

• Familiarity with embedded or real-time computing systems

• Familiarity with vehicle simulation tools (e.g. CarMaker)

• Strong analytical and problem-solving skills

Why you should join Geely 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 Geely 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. Applicants may specify preferred partner in their cover letter.

Supervisor: Karthik Prasad, Expert Motion Systems, [email protected], please contact for more information about the project

Starting date: January 2027

Last application date:2027-10-31

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.