Research Fellow (Learning-based Control)
NATIONAL UNIVERSITY OF SINGAPORE
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:
Job Description
We are seeking a Postdoctoral Research Fellow to develop uncertainty-aware, safety-critical autonomy for robots operating in open-world environments. The fellow will design methods that quantify confidence in prediction, synthesize formally safe interaction policies, and deliver real-time implementations on robotic platforms (e.g., mobile robots, autonomous driving stacks, or manipulation/humanoids). The position emphasizes theory and deployment: safety guarantees that hold under uncertainty, implemented in efficient C++/Python systems.
Key responsibilities:
• Design safety frameworks (e.g., CBF/CLF, stochastic/robust MPC, reachability, invariance) with learning components (Bayesian models, online uncertainty estimation, diffusion or policy learning) that preserve hard constraints.
• Model uncertainty for perception and dynamics (e.g., incremental Bayesian learning, predictive uncertainty calibration) and confidence-aware decision making.
• Implement optimization at scale (ADMM/consensus, parallelization) for real-time trajectory generation with barrier/constraint augmentation.
• Systems & validation: build reproducible stacks (C++/ROS/ROS 2, GPU acceleration where helpful), run hardware-in-the-loop and field experiments, maintain high-quality, well-tested code.
Qualifications
• Ph.D. in Robotics, Electrical and Computer Engineering, Mechanical Engineering, Computer Science, or a related field.
• Strong background in robotics, control, optimization, and machine learning.
• Experience in modeling uncertainty in machine learning using probabilistic techniques.
• Proven publication record in relevant venues (e.g., IEEE T-RO/T-AC/T-CST/RA-L, ACC/ECC/CDC, RSS/ICRA/IROS/ITSC).
• Hands-on skills in C++ and Python (modern tooling, profiling, testing) and ROS/ROS 2
• Demonstrated ability to take methods from paper to working robot systems (simulation + real hardware).
• Open to Fixed Term Contract.
Your application will be processed only if you apply via NUS Career Portal
We regret that only shortlisted candidates will be notified.
Job Description:
Job Description
We are seeking a Postdoctoral Research Fellow to develop uncertainty-aware, safety-critical autonomy for robots operating in open-world environments. The fellow will design methods that quantify confidence in prediction, synthesize formally safe interaction policies, and deliver real-time implementations on robotic platforms (e.g., mobile robots, autonomous driving stacks, or manipulation/humanoids). The position emphasizes theory and deployment: safety guarantees that hold under uncertainty, implemented in efficient C++/Python systems.
Key responsibilities:
• Design safety frameworks (e.g., CBF/CLF, stochastic/robust MPC, reachability, invariance) with learning components (Bayesian models, online uncertainty estimation, diffusion or policy learning) that preserve hard constraints.
• Model uncertainty for perception and dynamics (e.g., incremental Bayesian learning, predictive uncertainty calibration) and confidence-aware decision making.
• Implement optimization at scale (ADMM/consensus, parallelization) for real-time trajectory generation with barrier/constraint augmentation.
• Systems & validation: build reproducible stacks (C++/ROS/ROS 2, GPU acceleration where helpful), run hardware-in-the-loop and field experiments, maintain high-quality, well-tested code.
Qualifications
• Ph.D. in Robotics, Electrical and Computer Engineering, Mechanical Engineering, Computer Science, or a related field.
• Strong background in robotics, control, optimization, and machine learning.
• Experience in modeling uncertainty in machine learning using probabilistic techniques.
• Proven publication record in relevant venues (e.g., IEEE T-RO/T-AC/T-CST/RA-L, ACC/ECC/CDC, RSS/ICRA/IROS/ITSC).
• Hands-on skills in C++ and Python (modern tooling, profiling, testing) and ROS/ROS 2
• Demonstrated ability to take methods from paper to working robot systems (simulation + real hardware).
• Open to Fixed Term Contract.
JOB SUMMARY
Research Fellow (Learning-based Control)
NATIONAL UNIVERSITY OF SINGAPORE
Singapore
3 days ago
N/A
Full-time
Research Fellow (Learning-based Control)