Senior Robotics Researcher Learning Based Motion Planning - Contractor

Institute and research centre

Role overview

Key responsibilities

• Develop, adapt, and deliver motion-planning solutions that meet agreed client requirements.
• Formulate behavior, path, and trajectory planning problems that account for vehicle kinematics, dynamics, environmental constraints, and uncertainty.
• Develop and evaluate model-based planning and constrained trajectory optimization, including search-based methods, optimal control, and model predictive control.
• Investigate learning-based and hybrid approaches and compare their benefits with model-based alternatives.
• Design simulation and robot-data experiments; prepare data and train models where appropriate.
• Evaluate performance, robustness, constraint satisfaction, and computational efficiency through reproducible closed-loop experiments and comparative studies.
• Transfer validated methods into documented, reusable MPLAN software and support integration, testing, and deployment with engineers.
• Mentor engineers and students, collaborate across application teams, contribute to technical direction, and lead publications and technical reports.

Required qualifications

• Ph.D. in Robotics, Control, Applied Mathematics, Computer Science, Engineering, or a related field, or equivalent demonstrated research experience.
• Strong foundations in motion planning, control theory, robot kinematics and dynamics, mathematical optimization, probability, and numerical methods.
• Demonstrated research and implementation experience in model-based motion planning, optimal control, or constrained trajectory optimization for robotic systems.
• Research experience applying machine learning to motion planning or control, with implemented results and understanding of benefits and limitations.
• Strong publication record with substantial contributions in robotics or control, including equivalent venues to those listed in the posting.
• Strong C++ and/or Python programming skills, planning-algorithm implementation and testing, and experience with PyTorch or an equivalent ML framework.
• Experience evaluating algorithms in closed-loop robotic simulation, including failure analysis, model mismatch, and computational constraints.

Desirable experience

• Experience developing, integrating, or testing planning or control algorithms on real autonomous vehicles, including ground, marine, or UAV platforms, is desirable.
• Imitation learning, reinforcement learning, temporal models for robotics, and sensor-to-trajectory planning are desirable areas of experience.
• ROS 2, real-time implementation, simulation-to-reality transfer, and robotic-hardware deployment experience are desirable.