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

Some Research Fellow positions are open in the research group of Prof. Shuzhi Sam Ge at the Department of Electrical and Computer Engineering, National University of Singapore (NUS).
Job Description
This project aims to develop an intelligent switching control framework that integrates advanced robot modeling, adaptive control strategies, and machine learning-based self-adaptation with enhanced security against physical-world adversarial attacks.
The successful candidate is required to:
• Modeling MR² platforms under nonholonomic constraints and various configurations;
• Designing adaptive switching control algorithms for reconfiguration and mode transition;
• Investigating adversarial robustness under real-world constraints such as lighting, weather, and viewpoint changes;
• Developing multi-modal attack and defense strategies involving camera, LiDAR, and radar sensors;
• Ensuring temporal consistency in adversarial robustness and designing sequence-based defenses;
• Integrating reinforcement learning or self-supervised learning for environment generalization;
• Deploying and validating the system on simulation platforms and digital twins.

Qualifications

• Ph.D. Degree in Robotics, Control Engineering, Computer Science, Mechanical Engineering, or a related discipline;
• Solid background in control theory, particularly in switched systems, adaptive control, robotic modeling, or dynamic systems;
• Experience in mobile robot design, modular robotics, or nonholonomic system control is highly desirable;
• Prior knowledge or demonstrated interest in reinforcement learning, hierarchical learning, or transfer learning is a strong plus;
• Proficiency in one or more programming and simulation environments, such as MATLAB/Simulink, Python, C++, or ROS;
• Experience with adversarial learning, sensor fusion, or reinforcement learning is highly desirable;
• Hands-on experience with multimodal sensor integration.