This PhD position offers a unique opportunity to advance safe and transparent control for autonomous, over-actuated electric vehicles. You will work at the intersection of model predictive control and machine learning to tackle the complexity of force allocation and motion planning under uncertainty and actuator failures. The project combines theoretical research in stochastic optimal control with real-world applications, in collaboration with Volvo Cars and Volvo Group. This is an ideal position for candidates interested in interpretable AI, safety guarantees, and high-impact research in safe and sustainable mobility.

QUALIFICATIONS

To be eligible for this position, you must have (or be close to completing) a Master’s degree corresponding to at least 240 higher education credits in Applied Mathematics, Applied Physics, Electrical Engineering, Mechanical Engineering, or a related field. A strong mathematical foundation and excellent academic performance are expected.

Required qualifications:

• Proficiency in programming (primarily Python or MATLAB)
• Strong communication and collaboration skills, including the ability to work across research groups and disciplines
• Excellent written and spoken English
• Experience with optimal control theory and methods

As a PhD student, your primary responsibility is to conduct high-quality research on interpretable and learning-based stochastic optimal control for over-actuated electric vehicles, with a focus on ensuring robustness and fail-safe operation. You will:

• Develop modular, scalable, and transparent control algorithms suitable for real-time implementation across different vehicle platforms.
• Contribute to theoretical developments in stochastic model predictive control and its integration with learning-based motion prediction under uncertainty.
• Validate methods through simulation and collaboration with industrial partners (Volvo Cars and Volvo Group).
• Publish results in leading journals and present at international conferences.