3 dagen geleden - Radboud Universiteit (RU) - Nijmegen
PhD Position Multi-robot coordination under uncertainty
This PhD position will allow you to investigate game theory and reinforcement learning in the context of multi-robot coordination, including perception-aware and communication-aware motion planning.
- Mekelweg, Delft, Zuid-Holland
- Tijdelijk contract / Tijdelijke opdracht
- Uren per week:
- 36 - 40 uur
- € 2395 - € 3061 per maand
Autonomous robots (such as cars and UAVs) will be widespread in our daily lives. These robots will operate near humans in complex dynamic environments. To safely coordinate, these robots will benefit from exchanging a large amount of information, for example for perceiving and understanding a complex dynamic environment. However, exchanging large amounts of data is not always possible due to bandwidth constraints, faults and delays.
This project will allow you, as a PhD candidate, to design coordination strategies for the robots to limit the amount of information exchanged among the robots, while preserving safety. To achieve these objectives, you will investigate how to combine reinforcement learning (RL) and game theory to devise a multi-agent RL framework to safely coordinate the robots with limited communication exchanges. For example, the proposed method might decide with whom, when and what information to share for efficient perception-aware and communication-aware distributed motion planning.
You will be able to test your algorithms in practice in our experimental facilities, designing experiments on real autonomous robots (e.g., UAVs or ground robots) to demonstrate the effectiveness of the proposed design.
For your PhD you will be embedded within the Autonomous Multi-robots Lab in the Department of Cognitive Robotics at TU Delft. For more information of our ongoing research see https://www.autonomousrobots.nl.
Starting date is flexible between 1st September 2021 and 31st December 2021.
The candidate has a MSc degree in Systems and Control, Computer Science, Applied Mathematics, Robotics, or a related field. The candidate must be able to work at the intersection of several research domains and have a passion for doing ground-breaking theoretical research and applying it to real robots. Good programming skills and experience with programming languages such as Python and C++ are of foremost importance. Excellent command of the English language is required, as well as excellent communication skills. Candidates with a background in numerical optimization, control theory or robotics are especially encouraged to apply. Experience with game theory, perception and/or reinforcement learning algorithms is a strong plus. Nevertheless, candidates with interest in other multi-robot research domains (e.g., distributed SLAM) can also apply.
TU Delft offers PhD-candidates a 4-year contract, with an official go/no go progress assessment after one year. Salary and benefits are in accordance with the Collective Labour Agreement for Dutch Universities, increasing from € 2395 per month in the first year to € 3061 in the fourth year. As a PhD candidate you will be enrolled in the TU Delft Graduate School. The TU Delft Graduate School provides an inspiring research environment with an excellent team of supervisors, academic staff and a mentor. The Doctoral Education Programme is aimed at developing your transferable, discipline-related and research skills.
The TU Delft offers a customisable compensation package, discounts on health insurance and sport memberships, and a monthly work costs contribution. Flexible work schedules can be arranged. For international applicants we offer the Coming to Delft Service and Partner Career Advice to assist you with your relocation.