Interested applicants are invited to apply directly at the NUS Career Portal
Your application will be processed only if you apply via NUS Career Portal
We regret that only shortlisted candidates will be notified.
Job Description
• Possess a Ph.D. Degree in either Electrical Engineering or strictly related (e.g., Mathematics, Computer, Communication, Mechanical, or Information Engineering).
• Have substantial research experiences in quadrotor path planning and control, SLAM, learning-based control, practical reinforcement learning, model predictive control.
• Proficient in C++ or Python. Familiar with machine-learning tools and packages. Familiar with various 3D simulation environments for quadrotor simulations. Familiar with ROS and quadrotor control algorithms.
• Possess a strong academic record proved through coursework (especially math-intensive courses) and projects during his/her undergraduate and doctoral studies.
• Strong publication records in leading journals and conferences are highly valued
• Excellent communication skills as he/she is required to publish and present results at conferences and journals independently.
• Activity performed in world-class research environments is highly valued.
• Open to Fixed Term Contract.
Qualifications
A Research Fellow (RF) position is open in the research group of Assistant Professor Zhao Lin, at the Department of Electrical and Computer Engineering, National University of Singapore (NUS).
The Research Fellow will work closely with the Principal Investigator (PI) on reinforcement learning control and learning-based control, which leverage the advantages of both deep learning and conventional controls with theoretical guarantees.
The RF will develop AI-assisted planning and control algorithms that enable intelligent and robust autonomous operations and multi-agent cooperative transport. The approach will leverage the advantages of both deep reinforcement learning and conventional controls, combining model-based and model-free methods. Strong hardware experience and C++ coding especially related to quadrotor path planning and control are required.
The initial appointment duration is 12 months, which can then be extended based on an evaluation at the end of the initial appointment.
The research project involves (1) theoretical research in control, learning, and optimization, (2) developing new control and learning algorithms, and (3) 3D Simulations and real hardware experiments.
The candidates will be responsible for conducting theoretical research and real hardware experiments. The candidates are expected to help the PI supervise junior PhD students as well.
The candidates should have a Ph.D. degree from a reputable university, with expertise in quadrotor path planning and control, deep reinforcement learning, etc.
A successful candidate should have a solid mathematical background (such as in calculus, linear algebra, optimization, etc.). Strong publication records in leading journals and conferences are highly valued. Practical hands-on experience in autonomous quadrotors is preferred.
