Postdoc: Safe Reinforcement Learning for Motion Planning: Theory

Research / Academic

Reinforcement learning (RL) is showing increasing potential in real-world robotic applications, however, theoretical guarantees for RL such as stability, robustness and safety are still missing. The goal of this project is to close the gap between control theory and black-box RL methods and produce a stability-guaranteed RL method with a focus in home robotics applications. The PostDoc will explore how to guarantee the stability properties in RL for the general class of nonlinear stochastic systems. In this project, we will collaborate with AnKobot to develop novel smart and safe cleaning robots’ concepts. 


The candidate is expected to be able to explore tools in both control theory, machine learning, stochastic process and probability theory. Thus, we are looking for a candidate with a PhD degree in systems and control, robotics, applied mathematics, artificial intelligence, machine learning, or a related subject. The candidate must have strong analytical skills and must be able to work at the intersection of several research domains. Experience with study on stochastic process is a plus. Experience with real robot applications is also a plus. The applicant should have demonstrated ability to conduct high-quality re-search according to international standards, as demonstrated by publications in international, high-quality journals. A very good command of the English language is required, as well as excellent communication skills. 

Salary Benefits:

TU Delft offers a customisable compensation package, a discount for health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. An International Children’s Centre offers childcare and an international primary school. Dual Career Services offers support to accompanying partners. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities.   

Work Hours:

38 hours per week


Mekelweg 2