Research Fellow: Multi-Agent Drone Path Planning

Nanyang Technological University Singapore; Singapore; On-site; SGD 60,000 - 100,000; Full time

Job summary

NTU Singapore invites applications for a Research Fellow in Multi-Agent Path Planning for Autonomous Drone Operations. The role focuses on learning-based MPC algorithms for multi-agent drone navigation around vessels in maritime environments, including safety buffers, corridor allocation, and capacity limits under varying traffic.

The candidate will develop MPC algorithms, model predictive control methods, and simulation-based validation, working with PhD students and project collaborators to

Qualifications

• PhD in Robotics, Aerospace, Mechanical, Electrical/Electronic Engineering, Computer Science, AI or related discipline.
• Strong research background in multi-agent reinforcement learning, multi-robot systems or learning-based navigation.
• A strong publication record in relevant journals or conferences would be an advantage.

Responsibilities

• Develop multi-agent path-planning frameworks for safe and efficient multirotor operations in maritime environments.
• Formulate navigation problems with state/action representation, safety constraints, vessel volumes and trajectory optimisation.
• Create MPC and multi-agent MPC algorithms for path planning under dynamic maritime conditions.
• Develop capacity-optimisation algorithms to respond to vessel movements and environmental disturbances.
• Integrate drone airspace usage prediction and vessel estimates within a simulation-based validation framework.
• Design experiments, perform sensitivity analyses and validation studies for navigation safety and robustness.

Skills

Python programming

Reinforcement learning

Multi-agent systems

Autonomous navigation

Education

PhD in Robotics or related field

Tools

PyTorch

TensorFlow

ROS/ROS2

Gazebo

AirSim

Unity

Job description

NTU Singapore invites applications for a Research Fellow in Multi-Agent Path Planning for Autonomous Drone Operations. The role focuses on learning-based MPC algorithms for multi-agent drone navigation around vessels in maritime environments, including safety buffers, corridor allocation, and capacity limits under varying traffic.

The candidate will develop MPC algorithms, model predictive control methods, and simulation-based validation, working with PhD students and project collaborators to