Research Fellow (Multi-Agent Path Planning for Autonomous Drone Operations)

This Research Fellow position focuses on developing learning-based model predictive control (MPC) algorithms for multi-agent multirotor drone navigation around vessels in maritime environments. The role involves integrating crash predictions with vessel protected volume estimates, developing multi-agent path-planning and machine-learning methods for corridor allocation and airspace capacity optimisation. The researcher will work with PhD students, research engineers, and project collaborators to support system integration, testing, and validation, and will prepare technical reports and publications.

Responsibilities

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

Requirements

• 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.
• Strong communication and problem-solving skills.
• Strong sense of ownership, responsibility, and initiative.
• Ability to mentor junior researchers, PhD students, or research engineers and collaborate with industry partners, and project stakeholders.
• Willingness to support project reporting and milestone reviews.
• Strong programming skills in Python and deep learning frameworks such as PyTorch or TensorFlow.
• Experience in autonomous navigation, path planning, trajectory optimisation, conflict detection, or collision avoidance.
• Experience in model predictive control and multi-agent model predictive control algorithms.
• Familiarity with optimisation techniques, machine-learning methods and data-driven modelling.
• Familiarity with robotics and autonomous-system simulation environments such as ROS/ROS2, Gazebo, AirSim, Unity, or equivalent platforms.
• Experience in developing learning-based model predictive control algorithms in simulation.
• Experience in multi-agent robotic systems, drone swarms, or autonomous decision making.
• Experience in integrating prediction, planning, decision-making, and control modules within a simulation or experimental framework.
• Ability to formulate and solve navigation and optimisation problems under uncertainty, dynamic constraints, and changing operational conditions.
• 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

Nice to have

• A strong publication record in relevant journals or conferences would be an advantage.
• Knowledge of vessel-motion prediction, dynamic obstacle avoidance, separation assurance, or traffic-aware navigation would be advantageous.
• Familiarity with geospatial data, maritime traffic data, Automatic Identification System data, or airspace-capacity modelling would be beneficial.
• Experience with control algorithms for embodied AI systems is desirable.