close

Postdoc: Safe Reinforcement Learning for Motion Planning: Simulator

Research / Academic
Delft

An open-source real-world simulation environment will be built by incorporating physics engine and perception algorithms to test reinforcement learning algorithms. The PostDoc will establish a standard test set that considers multiple influencing factors such as multiple platforms, multiple operating conditions and multiple system configurations. A flexible and reliable task configuration reference standard for different scenarios can be derived. In this project, we will collaborate with AnkoBot to develop novel smart and safe cleaning robots’ concepts. 

Requirements:

The candidate is expected to have background and interest in control theory, machine learning and software/hardware system development. Knowledge on unmanned system, motion planning, and/or ROS will be an advantage. 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

Address:

Mekelweg 2