← All open positions

Doctoral Position in Communication-Aware Multi-Agent Reinforcement Learning for Heterogeneous Lunar Robot Teams

Project
ADA-COLLAB
Expected start
Summer 2027
Application deadline
to be confirmed

SnT is a leading international research and innovation centre in secure, reliable and trustworthy ICT systems and services. We play an instrumental role in Luxembourg by fueling innovation through research partnerships with industry, boosting R&D investments leading to economic growth, and attracting highly qualified talent.

The Centre is rapidly expanding its research activities and is seeking highly motivated doctoral candidates who wish to pursue research in close cooperation with our partners. For further information you may check: www.securityandtrust.lu, www.spacer.lu, https://wwwen.uni.lu/snt/research/spacer

We’re looking for people driven by excellence, excited about innovation, and looking to make a difference. If this sounds like you, you’ve come to the right place!

  • The initial contract is 36 months, with a further possible 1-year extension if required.
  • On a full-time basis (40hrs/week).
  • Employee and student status.
  • Expected start: Summer 2027

Position Description

The successful candidate will join a strong and motivated research team led by Prof. Miguel Olivares-Mendez (Space Robotics (SpaceR) research group) in collaboration with the partners of the Horizon Europe project ADA-COLLAB, including DLR, to carry out research to pursue a PhD on the following topic:

Communication-aware multi-agent reinforcement learning for the decentralised coordination of heterogeneous lunar robot teams.

About the project

ADA-COLLAB (Horizon Europe, February 2027 – January 2031) brings together 28 partners coordinated by Sorbonne Université, including CNRS, IIT, DLR and ONERA, to build ADAa: a brain-inspired cognitive architecture that makes AI agents built on large multimodal models autonomous, collaborative and dependable, with ethics by design in line with the EU AI Act. It is validated in three demonstrators (cultural heritage, stroke rehabilitation and space robotics). SpaceR leads the validation and demonstrators work package and the space use case: a team of lunar robots coordinated by multi-agent reinforcement learning and supervised through natural-language mission control, with a final demonstration with DLR.

In its space use case, a heterogeneous team of lunar robots (scout rovers, a manipulation rover and a lander) must coordinate with limited and changing communications, under partial observability, while a human supervises the mission. The PhD will develop multi-agent reinforcement learning methods for decentralised coordination, communication-aware navigation, formation control and dynamic relay networks. Policies will be trained in SpaceR’s open-source Space Robotics Bench and validated in the LunaLab and at a lunar analogue site with DLR.

The position holder will be required to perform the following tasks:

  • Carrying out research in the predefined areas
  • Developing multi-agent reinforcement learning policies for the scout rovers and the communication link with the lander
  • Contributing to the multi-agent extension of the Space Robotics Bench
  • Disseminating results through scientific publications
  • Contribute to the development of experiments on real and analogue environments
  • Collaborate with other team members on joint publications and experiments

Qualification: The candidate should possess an MSc and bachelor’s degree in Computer Science, Artificial Intelligence, Robotics or Aerospace Engineering with a GPA of 3.2+. We expect a candidate who is passionate about reinforcement learning and multi-robot systems.

Experience: The ideal candidate must have experience on

  • Knowledge of programming languages (Python and/or C++)
  • Strong understanding of Reinforcement Learning (e.g. PPO, SAC) and deep learning frameworks (PyTorch)
  • Excellent written and spoken communication skills in English

In addition, the candidate should have experience in some of the following topics:

  • Experience with multi-agent reinforcement learning (e.g. MAPPO, QMIX)
  • Experience with multi-robot systems or networked/communication-aware planning
  • Experience with GPU simulators (Isaac Sim/Isaac Lab, MuJoCo) and Gymnasium
  • Knowledge of ROS 2

Language Skills: Fluent written and verbal communication skills in English are required.

Offer

The University offers a Ph.D. study program with an Initial contract of 36 months, with a possible one-year extension if necessary. It offers highly competitive salaries and is an equal-opportunity employer. You will work in an exciting international environment and have the opportunity to participate in the development of a newly created university.

Application

Application should include

  • Full CV, including list of publications and name (and email address, etc) of three referees
  • Transcript of all modules and results from university-level courses taken
  • Short motivation letter

All qualified individuals are encouraged to apply.

Deadline for applications: to be confirmed

About the University of Luxembourg

University of Luxembourg is an international research university with a distinctly multilingual and interdisciplinary character. The University was founded in 2003 and counts more than 6,700 students and more than 2,000 employees from around the world. The University’s faculties and interdisciplinary centres focus on research in the areas of Computer Science and ICT Security, Materials Science, European and International Law, Finance and Financial Innovation, Education, Contemporary and Digital History. In addition, the University focuses on cross-disciplinary research in the areas of Data Modelling and Simulation as well as Health and System Biomedicine. Times Higher Education ranks the University of Luxembourg #3 worldwide for its “international outlook,” #20 in the Young University Ranking 2021 and among the top 250 universities worldwide.

Further information

For further information, please contact us at miguel.olivaresmendez@uni.lu