PhD Candidate in Hybrid Learning-Control Methods for Autonomous Underwater Manipulation

This is NTNU NTNU is a broad-based university with a technical-scientific profile and a focus in professional education. The university is located in three cities with headquarters in Trondheim. At NTNU, 9,000 employees and 43,000 students work to create knowledge for a better world. You will find more information about working at NTNU and the application process here.

Video: https://youtu.be/Xt-yHCN5QS0About the position The position is for three years with the possibility of up to one-year extension for teaching assistant duties, and is part of the Norwegian Centre for Embodied AI (NCEI), one of Norway’s six national AI centres. The centre is recruiting outstanding researchers to advance a universal science of embodied intelligence. NCEI brings together leading robotics and AI groups with key partners from industry and the public sector to study how intelligence emerges from the interaction between body, computation, and environment, across flying, ground, and aquatic robot configurations. Our mission is to chart a generalisable path for physical AI and transform how robot morphology and autonomy are co-designed, enabling new generations of systems tailored to their operational environments and missions. Successful candidates will join an international community with world-class facilities and strong collaborations across Norwegian universities, research institutes, industry, public agencies, and leading global institutions. We welcome motivated applicants in robotics, control, AI, machine learning, physics, and related fields, including early-stage researchers eager to contribute to this emerging scientific frontier.

About the project The role of the PhD candidate will be to develop efficient methods for Hybrid Learning-Control Methods for Autonomous Underwater Manipulation: Modern AI has demonstrated remarkable capabilities in learning, adaptation, planning, and decision-making. However, autonomous underwater manipulation presents challenges that remain difficult for purely data-driven methods, including safety-critical operation, uncertain environments, limited data availability, and the need for reliable performance guarantees. In this project, you will investigate how the strengths of modern machine learning can be combined with the rigorous foundations of control systems theory to create a new generation of intelligent underwater robotic systems. The research will focus on developing hybrid learning–control architectures that integrate model-based control and planning methods with data-driven learning approaches. Potential topics include safe reinforcement learning, learning-based adaptation and control, physics-informed machine learning, learning-enhanced model predictive control, control-theoretic safety and stability guarantees for learning-enabled systems, and the integration of foundation models with autonomous robotic decision-making and control. The methods developed will be validated on advanced underwater robotic platforms performing challenging manipulation tasks such as object retrieval, inspection, intervention, and maintenance operations. This position offers a unique opportunity to contribute to one of the most exciting frontiers in robotics and AI: combining the best of modern learning methods with the best of control systems theory. The ultimate goal is to develop autonomous underwater robots that can learn, adapt, and make intelligent decisions while retaining the reliability, robustness, and safety required for operation in complex real-world environments. The PhD candidate will be supervised by Professor Kristin Y. Pettersen, with Professor Jan Tommy Gravdahl as co-supervisor.

Duties of the position • Complete your doctoral education leading to the PhD degree. • Conduct and publish research of high quality within the framework described above. • Participate in international activities such as conferences and/or research stays abroad. • Collaborate with other researchers within the department and across departments at NTNU. • Supervise master’s thesis students related to the project. • Upon agreement with the candidate and the department, the position may be extended if the candidate undertakes career-enhancing work beyond the research project, such as teaching duties. Be prepared for changes to your work duties after employment.

Required selection criteria • You must have a Master's degree in cybernetics, control systems, or equivalent, with a strong training in control of marine vehicles and/or robots. Additional training in machine learning methods is an advantage. Your degree must correspond to a five-year Norwegian program, where 120 credits have been obtained at master's level. Master’s students in their final year are welcome to apply; employment will then be postponed until the master’s degree is completed. • You must have a strong academic background from your previous studies and have an average grade from your Master's degree study, or equivalent education, which is equal to B or better compared to NTNU's grading scale. If you do not have letter grades from previous studies, you must have an equally good academic foundation. If you have slightly weaker grades, you may be considered if you can document that you are particularly suitable for a PhD education. • You must fulfil the admission requirements for the PhD program at the Faculty of Information Technology and Electrical Engineering. • Applicants who do not master a Scandinavian language and do not have English as mother tongue, must document English proficiency through one of the following tests: TOEFL, IELTS or Cambridge Certificate in Advanced English (CAE) or Cambridge Certificate of Proficiency in English (CPE). Minimum scores are: TOEFL: 600 (paper-based test), 92 (Internet-based test), IELTS: 6.5, with no section lower than 6.5 (only Academic IELTS test accepted), CAE or CPE certificate with a minimum score of 180. • Our research has civilian objectives. However, equipment restricted by export licenses and ITAR (International Traffic in Arms Regulations) are being used in the research project. Applicants who are citizens of Norway, EU, Switzerland, Australia, Japan, New Zealand, or NATO countries are eligible. Other applicants are required to provide evidence of their eligibility to work with such equipment for their application to be considered. PLEASE NOTE: For detailed information about what the application must contain, see paragraph “About the application”. The appointment is to be made in accordance with NTNUs guidelines for recruitment positions and the general criteria for the position.

Preferred selection criteria • A solid theoretical background in nonlinear control and the control of marine vehicles or robotic systems. • Additional training in machine learning methods is an advantage. • Solid programming skills. • Strong skills in mathematics, excellent capacity for mathematical formalism, and ability to grasp new concepts quickly.

Personal characteristics To successfully complete a doctoral degree (PhD), it is important that you are able to: • Work independently and in a structured way, set goals and make plans to achieve them. • Demonstrate strong analytical and communication skills, and ability to discuss and present research clearly. • Willingness to learn, show curiosity and a strong motivation for the subject. • Be open to exploring topics outside your comfort zone, generate new ideas, and engage in constructive, critical discussions with your supervisors to evaluate research ideas. • Perseverance and the ability to work effectively under pressure or in the face of adversity. Emphasis will be placed on personal suitability.

We offer • An exciting job with an important mission in society • Developing tasks in a strong and international professional environment • Career guidance and follow-up during the PhD period • Open and inclusive working environment with committed colleagues • Working capital that can be used to imple