Delft University of Technology
Top university
Just Landed
New Today
PhD Position in Safe Planning and Decision-Making under Uncertainty for Long-Horizon Robot Autonomy Delft University of Technology in Netherlands
Degree Level
PhD
Field of study
Computer Science
Funding
PhD employment for 4 years in principle, structured as an initial 1.5-year contract followed by a 2.5-year contract contingent on progress. Salary ranges from €3059 to €3881 gross per month across years 1 to 4 for a full-time 38-hour contract, plus 8% holiday allowance and an 8.3% end-of-year bonus. Additional benefits include a customizable compensation package, discounts on health insurance, and a monthly work costs contribution.
Deadline
Nov 15, 2026
Country
Netherlands
University
Delft University of Technology
Apply for this position
You'll sign in first, then continue in your ApplyKite dashboard.
Keywords
Suggested positions
About this position
PhD opportunity at Delft University of Technology (TU Delft) in the Cognitive Robotics Department and the Faculty of Mechanical Engineering, working within the EU-funded OPERA consortium and the Reliable Robot Control Lab. The project focuses on safe planning and decision-making under uncertainty for long-horizon robot autonomy, with an emphasis on methods that let robots operate safely and reliably over long time horizons in human-centered environments.
The research sits at the intersection of robotics, control, optimization, motion planning, probabilistic modeling, state estimation, and learning-based methods. The successful candidate will develop planning and decision-making methods that balance safety, performance, and real-time computation, and will analyze their guarantees and failure modes. Depending on background, the work may involve optimal control, model predictive control, motion planning, probabilistic/Bayesian modeling, uncertainty quantification, or model-based reinforcement learning. The methods will be validated in simulation and on real robots, and connected to OPERA tasks on GPAI-powered planning, long-term reasoning, and adaptive human-robot interaction.
Eligibility highlights: an MSc in Systems and Control, Robotics, Applied Mathematics, or a closely related field; strong mathematical and analytical skills; excellent English; and a genuine interest in rigorous research on safe robot autonomy. Experience with optimization-based planners/controllers, C++ or Python, acados or CasADi, robust control, ROS/ROS 2, or real-robot deployment is especially welcome.
Funding: this is a salaried PhD employment position for 4 years in principle, with salary from €3059 to €3881 gross per month plus holiday allowance and an end-of-year bonus. TU Delft also offers health insurance discounts and a monthly work costs contribution.
Application deadline: 15 November 2026. Apply online through the TU Delft careers portal and include a motivation letter, CV, transcripts, and MSc thesis (or draft/link). Applications are to be addressed to Laura Ferranti and Robert Babuska.
Funding details
PhD employment for 4 years in principle, structured as an initial 1.5-year contract followed by a 2.5-year contract contingent on progress. Salary ranges from €3059 to €3881 gross per month across years 1 to 4 for a full-time 38-hour contract, plus 8% holiday allowance and an 8.3% end-of-year bonus. Additional benefits include a customizable compensation package, discounts on health insurance, and a monthly work costs contribution.
What's required
Applicants should have an MSc degree in Systems and Control, Robotics, Applied Mathematics, or a closely related field. Strong interest in safe planning and decision-making for robots is required, along with rigorous theoretically grounded research skills and willingness to validate methods in simulation and on real robots. Strong analytical and mathematical skills in optimization, probability and statistics, and dynamical systems are expected. Excellent written and verbal English proficiency is required. Experience with optimization-based planners or controllers (e.g. MPC with acados or CasADi) in C++ or Python, safe or robust control under uncertainty, learned dynamics or model-based reinforcement learning, uncertainty quantification or Bayesian modeling, long-horizon or hierarchical planning, human/multi-agent prediction, and real-robot deployment with ROS/ROS 2 is particularly encouraged.
How to apply
Apply online via the application button on the TU Delft careers page no later than 15 November 2026. Upload a motivation letter, updated CV, Bachelor and Master transcripts, and a copy or draft of your MSc thesis (or a link to access it). Address the application to Laura Ferranti and Robert Babuska. Do not apply or inquire via LinkedIn, email, or post.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.
Make your next move.
Prepare your application
Review drafts and confirm requirements with the university.