Machine Learning for Advancing the Robot Intelligence

Abstract
Machine Learning has seen dramatic development recently. It is now time to bring this tremendous progress of AI to Robotics. As Boston Dynamics have already demonstrated, robots are physically capable of performing incredibly agile locomotion. However, the level of Robot Intelligence needs significant improvement. This PhD research project aims to advance the robot intelligence and autonomy by applying state-of-the-art machine learning approaches to robot perception, planning, and control. Reinforcement Learning, Deep Learning, and Self-supervised learning will be employed to give robots the ability to better understand the world around them, ultimately leading to something analogous to “common sense” for robots.

How to Apply 
Please contact Dr Petar Kormushev if you are interested in applying for this project. 

For more information on submitting a PhD application, please consult our application pages here. When you submit your application, please cite this project title in the 'how you are planning to fund your PhD' section.