Research Engineer (Learning-based Motion Planning)

National University of Singapore; Singapore; On-site; SGD 70,000 - 110,000; Full time

Benefits offered by this job

Fixed-term contract

Job summary

National University of Singapore is seeking a research engineer to advance safe interactive navigation and manipulation for mobile robots operating in complex, dynamic environments.

You will design robust obstacle avoidance algorithms, develop differentiable numerical solvers for trajectory optimization, and integrate planning with differentiable simulation to collect high-quality task data for vision-language-action learning.

Qualifications

• Master or Bachelor Degree in robotics, computer science, electrical/electronic engineering, etc.
• Extensive experience in robotic motion planning and control, obstacle avoidance, and contact-aware task execution.
• Real-world robot development and deployment experience, including humanoid robot systems.

Responsibilities

• Design robust obstacle avoidance algorithms for mobile robots in dynamic environments.
• Develop differentiable numerical solvers for trajectory optimization for contact-rich tasks.
• Integrate planning and control with differentiable simulation to build a trajectory data collection system for vision-language-action learning.

Skills

Robotics

Motion planning

C++

Python

Algorithms

Education

Bachelor's degree

Master's degree

Tools

MuJoCo

ISSAC

Job description

Job Description

The research project focuses on developing safe interactive navigation and manipulation capabilities for mobile robots operating in complex, dynamic environments.

The research engineer is expected to contribute to the following key aspects:
a) Design robust obstacle avoidance algorithms for mobile robots in dynamically changing environments, focusing on formal safety constraints and real-time performance in unpredictable conditions.

b) Develop specialized differentiable numerical solvers for trajectory optimization that generate informed motion trajectories for contact-rich manipulation tasks, handling complex dynamics and physical constraints efficiently.

c) Integrate planning and control algorithms with differentiable simulation technologies to build a trajectory data collection system that generates high-quality, diverse task data for vision-language-action learning, enabling seamless integration from human instructions to robotic actions in complex mobile manipulation scenarios.

Qualifications

• Master or Bachelor Degree in a relevant discipline, e.g. robotics, computer science, electrical/electronic engineering, etc.
• Extensive experience in robotic motion planning and control, especially in obstacle avoidance and contact-aware task execution with demonstrated expertise in real-world robotic applications.
• Substantial practical experience in real robot development and deployment, including humanoid robot systems.
• Strong mathematical background with solid knowledge in numerical optimization theory. Familiarity with semidefinite programming and its convex relaxation techniques is highly preferred.
• Proficient experience with various robotics simulators (e.g., MuJoCo, ISSAC) and excellent programming skills in C++ and Python with the ability to develop efficient, production-quality code.
• Open to Fixed Term Contract.