Robots capable of autonomous decision making will be employed more and more in work contexts that involve interaction with a team of humans. As an example, think about the deployment of a multi-human, multi-robot team for logistical operations, for search and rescue or even surgeries. In all these scenarios executable models of the behavior of a team of robots (think about controllers at supervision level) needs to ensure the meaningful progression towards the task while guaranteeing safety. How to model and realize such controllers in highly dynamic contexts, guaranteeing safety and meaningful progression towards the task remains a challenge. This is even more complicated when the low level behavior of the robots (i.e. perception or motion control level) are governed by (deep) learning algorithms whose outcome is difficult to predict at design time.
The PhD student will explore new approaches to model and realize controllers at supervision level for multi-human-multi-robots tasks in the presence of machine learning algorithms for perception and low level motion control. To facilitate the experimental set-up to validate the devised controllers, the PhD student can make use of the TechUnited RoboCup robots and consider the shared task to be a collaborative human-robot game. The TechUnited robots are already capable of playing games with humans at a basic level. The research will enable the next generation of collaborative multi-robot multi human systems capable of learning, adapting and interacting in a safe way.
TU/e will offer you plenty of opportunities for development. You can join the DISC (Dutch Institute for Systems and Control) school as well as several programs offered by TU/e for personal development.
We are looking for a very motivated candidate with eagerness to learn and approach problems from a fundamental as well as a practical perspective. When selected you will join the CST group of the Mechanical Engineering Department.
The
Control Systems Technology (CST;
website) group as part of the department of Mechanical Engineering (ME) has an internationally recognized reputation in mechatronics, precision motion control and robotics. CST targets areas in Precision Machines, Robotics, Biomedical and Automotive engineering by designing performance based controllers, intelligent machine and algorithm designs. CST has a track record of over twenty years in bringing state-of-the-art systems and control theory into new designs and high-tech applications.
The CST group has a track record in European projects. It was coordinator of the FP7 - ROBOEARTH project, is and has been participating in H2020 projects EUREYECASE, ROPOD, AUTOPILOT and more recently SAFE-UP and many more European and nationally funded projects (INTEREG, OPZUID, FAST).
Since 2005, CST is the main contributor to the TU/e RoboCup team, named Tech United, 5 times world champion ('12, '14, '16, '18, '19) in the Middle Size League and the 2019 world champion in the @Home Domestic Platform League with the TOYOTA Human Support Robot. The model-based, multidisciplinary-oriented approach has proven to be highly valuable in the field of robotics. The CST group is led by Prof. M. Steinbuch and has produced 5 start-ups in the past
10 years (Preceyes, MicroSure, Eindhoven Medical Robotics, Smart Robotics and recently RUVU- behavior for robots).