Supervisors: Arkadiusz Sitek (Health Informatics Research Group Leader) with cooperation of Przemysław Korzeniowski (Senior Postdoctoral Reasercher, Head of VR & Robotics)
Project starts: Q2 2022 (but depends on Candidate’s availability)
The project will investigate the use of Artificial Intelligence, Deep Learning, Simulation, Computer Vision and Robotics in hospital and/or operating room environment. Specifically, it will explore applications such as robotic assistance to medical staff, surgical teams and/or motion impaired patients.
The research will aim to deliver algorithms and/or prototypes for autonomisation of our state-of-the-art collaborative robot (Cobot). You will use and develop cutting edge software for training robots in simulated virtual environments via machine learning techniques such as Reinforcement Learning. Then, you will transfer the learned behaviors from simulated to real robot. For deep learning and robot training you will use our in-house AI-cluster (16xNVidia A100) and/or Prometheus – a 2.35 PFlops supercomputer (144xNvidia Tesla K40). You will join a thriving AI research community with many ongoing projects in healthcare.
We are looking for candidates with an enthusiasm for research, multidisciplinary collaboration and tackling challenging problems through teamwork. We are targeting candidates with an MSc in Computer Science, Machine Learning, AI or Robotics, but we would also consider exceptional STEM students providing that they have appropriate Computer Science skills. Research interests should be in machine learning. Ideal skills would include: programming (Python/C/C++) and ML frameworks (PyTorch/Tensorflow). Nice to have: robotics middleware (ROS), 3D engines (Unity3D, Unreal Engine, Omniverse, Bullet Physics) and knowledge of git.
You do not need to have a background in Robotics, but willingness to learn basic concepts and definitions is a requirement.