Edward Johns

Director

e.johns@imperial.ac.uk

Google Scholar

I am director of the Robot Learning Lab at Imperial College. I received a BA and MEng in Electrical and Information Engineering from Cambridge University, and a PhD in vision-based robot localisation from Imperial College, working with Guang-Zhong Yang in the Hamlyn Centre. Following my PhD, I spent a year as a postdoc at UCL working with Gabriel Brostow, and I then returned to Imperial College as a founding member of the Dyson Robotics Lab with Andrew Davison, where I led the robot manipulation team. In 2017, I was awarded a Royal Academy of Engineering Research Fellowship for my project "Empowering Next-Generation Robots with Dexterous Manipulation: Deep Learning via Simulation", and then in 2018 I was appointed as a Lecturer at Imperial College, and founded the Robot Learning Lab. Alongside leading the lab's research, I teach a graduate-level course on Reinforcement Learning.

In 2014, I received a Bachelors (BSc) with Honours in Physics from the University of St. Andrews. After working as an Implementation Engineer at Apttus for a year, I completed an MSc in Computer Science at Imperial College. More recently, I worked as a software developer for Prof. Kazunori Sakamoto at the National Institute of Informatics in Tokyo, and received an MSc in Machine Learning from University College London. For my Masters dissertation, I worked under the supervision of Prof. Gabriel Brostow on predicting the future in videos through semantic object segmentation. My current research interests lie at the crossroads of Computer Vision, Reinforcement Learning and Robotics, with particular emphasis on sim-to-real transfer for robot manipulation tasks.

Before beginning my PhD, I completed a Bachelor’s degree in Physics and a Master’s degree in Computing (Machine Learning) at Imperial College London. During my Master’s degree I completed my individual project under the supervision of Dr. Edward Johns. The focus of this project was on learning stochastic policies from demonstrations and a sparse reward function. My PhD will extend this project and will investigate methods for robot learning of contact-rich task from demonstrations and a sparse reward function, which are both safe and efficient, and are suitable for deployment in an industrial setting.

I received my Bachelor's degree in Physics and Structural Engineering at Bogazici University, Istanbul, Turkey, in 2015. Following that, I completed my Master's degree developing system identification and damage detection algorithms at MIT. I specifically worked on Bayesian model updating methods and explored deep learning for earthquake characterization. Before joining the Robot Learning Lab as a PhD student, I led the research efforts in a computer vision startup in Berlin, which focuses on re-engineering the way humans interact with computers. I am currently working on robot manipulation and long-horizon planning for complex tasks. 

I am currently a PhD student at Imperial College London working in the Hamlyn Centre and the Robot Learning Lab. I received my Bachelor’s in Biomedical Engineering in 2013 at University of Melbourne. Later, I received two Master’s degrees, in Mechatronics Engineering at University of Melbourne and in Medical Robotics and Image Guided Intervention at Imperial College London, both completed with Distinction. My research interest is in robot learning and adaption for complex tasks in surgical applications. The focus of the research is to achieve surgical task automation through Computer Vision, Reinforcement Learning, and Learning from Demonstrations.

I am a PhD student at Imperial College London working at the Dyson Robotics Lab, where I am co-supervised by Dr. Edward Johns and Prof. Andrew Davison. I completed my MRes with Distinction at the same lab working on multi-task and auxiliary learning. Prior to joining Imperial College, I obtained my BS with Honours in Mathematics and Electrical Engineering at the Penn State University. I have also interned at The Robotics Institute at Carnegie Mellon University, Tencent - YouTu Lab, and Adobe Research. My general research interest is to build learning frameworks which can induce learning algorithms automatically, with no or minimal human supervision. This includes learning a universal representation from various tasks; automating network architecture design with adaptation to different input signals; and showing a quick mastery of new tasks based on previous experiences.