Research Fellow - Multi-Agent Path Planning for Autonomous Drones

About the role

The School of Mechanical & Aerospace Engineering at Nanyang Technological University (NTU) is seeking a Research Fellow to develop learning-based model predictive control (MPC) algorithms for multi-agent multirotor drone navigation around vessels in maritime environments. The work integrates crash-prediction models with vessel protected-volume estimates to find safety-buffer overlaps, and develops path planning, corridor allocation and airspace capacity optimisation methods.

Key responsibilities

• Develop multi-agent path-planning frameworks for safe and efficient multirotor operations in maritime environments.
• Formulate navigation problems including state and action representation, safety constraints, vessel-protected volumes, route allocation and trajectory optimisation.
• Develop model predictive control and multi-agent MPC algorithms for dynamic maritime conditions.
• Develop capacity optimisation algorithms that let drones respond to vessel movements, environmental disturbances and changing constraints.
• Integrate airspace-usage prediction, vessel protected volume estimation, navigation, decision-making and control modules in a simulation-based validation framework.
• Estimate safe operational capacity under different vessel traffic, airspace and environmental scenarios.
• Design and run simulation experiments, sensitivity analyses and validation studies on safety, efficiency, robustness, scalability and generalisation.
• Work with PhD students, research engineers, vessel and drone operators and collaborators on integration, testing, validation and demonstration.
• Prepare technical reports, publications, presentations and project deliverables.

Required profile

• PhD in Robotics, Aerospace, Mechanical, Electrical and Electronic Engineering, Computer Science, Artificial Intelligence or a closely related field.
• 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 is an advantage.
• Willingness to mentor junior researchers and PhD students, and to support project reporting and milestone reviews.

Required skills

• Python and deep learning frameworks such as PyTorch or TensorFlow.
• Autonomous navigation, path planning, trajectory optimisation, conflict detection or collision avoidance.
• Model predictive control and multi-agent MPC.
• Optimisation, machine learning and data-driven modelling.
• Simulation tools such as ROS/ROS2, Gazebo, AirSim, Unity or equivalents.
• Advantageous: vessel-motion prediction, dynamic obstacle avoidance, separation assurance, geospatial and maritime traffic data, AIS and airspace-capacity modelling.