close

Postdoc: Learning for Self-Healing of Multi-Machine Systems

Research / Academic
Delft

The goal of this project is to design novel methods to ensure the normal operation of multi-machine systems for transport and logistics, in the presence of multiple defective components and high system uncertainty.

The post-doctoral researcher will conduct fundamental theoretical and algorithmic research on multi-agent reinforcement learning for fault-tolerant control with applications to maritime transport systems.  The researcher will join a multi-disciplinary team led by Dr. Vasso Reppa, Assistant Professor with the Department of Maritime and Transport Technology, and by Dr. Wei Pan, Assistant Professor, with the Department of Cognitive Robotics.

The post-doctoral researcher is expected to bridge the expertise of the two departments by integrating cognitive fault tolerant control and decentralized multi-agent reinforcement learning techniques for the self-healability of multi-machine systems in the maritime transport domain (e.g. autonomous ships, automated container terminals).

[1] Wen, Y., Yang, Y., Luo, R., Wang, J., & Pan, W. (2019). Probabilistic Recursive Reasoning for Multi-Agent Reinforcement Learning. International Conference on Learning Representation (ICLR).

[2] Reppa, V., Polycarpou, M. M., & Panayiotou, C. G. (2015). Decentralized isolation of multiple sensor faults in large-scale interconnected nonlinear systems. IEEE Transactions on Automatic Control

[3] Ferranti, L., Negenborn, R. R., Keviczky, T., & Alonso-Mora, J. (2018). Coordination of Multiple Vessels Via Distributed Nonlinear Model Predictive Control. In 2018 European Control Conference (ECC).

Requirements:

We are looking for a talented post-doctoral researcher with background and interest in control theory and machine learning; a track record of publications in high-quality journals and/or conferences; and an excellent command of the English language (knowledge of Dutch is not required). Additional knowledge on motion planning, distributed control and/or maritime transportation will be an advantage.

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