Physical AI Simulation-Driven Learning and Planning for Industrial Robots

About the role

ABB Robotics is offering a master’s thesis project focused on Physical AI for industrial robots. The work will explore how modern simulation and AI methods can support data‑driven learning and planning, culminating in a prototype evaluated on a realistic robot benchmark.

Key responsibilities

• Review state‑of‑the‑art simulation and AI methods relevant to robot control and planning.
• Select a problem formulation, implement a prototype, and evaluate its performance on a realistic robot benchmark or experimental setup.
• Investigate topics such as efficient simulation generation, Real2Sim gap reduction, sensor modeling, speed‑accuracy trade‑offs, or integration of foundation models with classical planning.

Required profile

• Enrolled in a Master of Science program in Robotics, Engineering Physics, Computer Science, Electrical/Mechanical Engineering, Applied Mathematics or a related field.
• Strong interest in control theory, planning, machine learning, system identification, or physics‑based modeling.
• Ability to work independently, take initiative, and address open‑ended technical problems in a structured way.
• Good written and spoken English skills.

Required skills

• Proficiency in Python.
• Basic programming knowledge in C/C++ (advantage).