The posting
The School of Mechanical & Aerospace Engineering (MAE)is a robust, dynamic and multi-disciplinary international research communitycomprising of world-class scientists and bright students. MAE prides itself inits excellent research capabilities in areas including advanced manufacturing,aerospace, biomedical, energy, industrial engineering, maritime engineering,robotics, etc. The school is equipped with state-of-the-art researchinfrastructure, housing a comprehensive range of cluster laboratories, test beddingfacilities, research centres/institutes and corporate laboratories.Cutting-edge research in MAE addresses the immediate needs of our industriesand supports the nation’s long-term development strategies. In the new era ofindustrial 4.0 and sustainable living, MAE is rigorous in developing newcompetencies to support the growth and competitiveness of our engineeringsector in the global landscape. MAE has grown to be leader in EngineeringResearch, ranking amongst the top engineering schools in the world.
For more details, please view https://www.ntu.edu.sg/mae/research.
We are looking for a Research Fellow in Multi-Agent RLfor Autonomous Drone Swarm to develop learning-based algorithms for cooperativetarget tracking in complex environments. The role will focus on multi-agentreinforcement learning, decentralized target assignment, occlusion-awaredecision-making, and communication-resilient coordination for autonomous droneteams operating in urban and cluttered environments.
Key Responsibilities:
- Develop learning-based frameworks for cooperative multi-agent robotic systems operating in complex environments.
- Formulate multi-agent decision-making problems, including state and action representation, reward design, task allocation, and decentralized policy learning.
- Develop reinforcement learning and multi-agent reinforcement learning algorithms for autonomous coordination and target-following tasks under uncertainty, partial observability, and dynamic environmental conditions.
- Develop perception-aware decision-making methods that enable autonomous agents to respond to changing target and environment conditions.
- Integrate perception, decision-making, and control modules within a simulation-based validation framework.
- Design and conduct simulation experiments to evaluate system performance, robustness, scalability, and generalization.
- Work with PhD students, research engineers, and collaborators to support system integration, testing, and demonstration.
- Prepare technical reports, research publications, presentations, and project deliverables.
Job Requirements:
Education qualifications
- PhD degree in Robotics, Aerospace Engineering, Mechanical Engineering, Electrical and Electronic Engineering, Computer Science, Artificial Intelligence, or a closely related discipline.
- Strong research background in multi-agent reinforcement learning, multi-robot systems, autonomous systems, or learning-based navigation.
- A strong publication record in relevant journals or conferences would be an advantage.
Soft skills
- Strong communication and problem-solving skills.
- Strong sense of ownership, responsibility, and initiative.
- Ability to mentor junior researchers, PhD students, or research engineers.
- Willingness to support project reporting and milestone reviews.
Hard skills
- Strong programming skills in Python and deep learning frameworks such as PyTorch or TensorFlow.
- Experience with reinforcement learning and multi-agent reinforcement learning algorithms.
- Familiarity with simulation environments for robotics or autonomous systems, such as Unity, ROS/ROS2, Gazebo, AirSim or equivalent platforms.
- Knowledge of multi-agent coordination, decentralized control, target assignment, or swarm robotics.
- Familiarity with graph neural networks, attention mechanisms would be advantageous.
- Experience with computer vision, sensor fusion, or multi-object tracking would be beneficial.
Experience
- Experience in developing and training reinforcement learning or multi-agent learning policies in simulation.
- Experience in multi-agent robotic systems, drone swarms, or autonomous vehicle coordination.
- Prior experience with real-world robotic or UAV experiments would be an advantage, but is not mandatory.
Competencies
- Ability to design robust learning algorithms under uncertainty and communication constraints.
- Ability to work across AI, robotics, control, and UAV autonomy domains.
- Ability to deliver research outcomes within project timelines and contribute to high-quality publications.
We regret to inform that only shortlisted candidates will be notified.
