top of page
At The Robot Learning Lab, we are developing advanced robots that are empowered by artificial intelligence, for assisting us all in everyday environments. Our research lies at the intersection of robotics, computer vision, and machine learning, and we are primarily studying robot manipulation: robots that can learn to physically interact with objects using their arms and hands. Applications include domestic robots (e.g. tidying the home), manufacturing robots (e.g. assembling products in a factory), and warehouse robots (e.g. picking and placing from/into storage). The lab is led by Dr Edward Johns in the Department of Computing at Imperial College London. Welcome!
DALL-E-Bot published in RA-Letters!
DALL-E-Bot is a robot's "imagination engine", enabling the robot to generate natural-looking goal images for object re-arrangement. This is the first work to study web-scale diffusion models for robotics.
Two papers published at CoRL 2022!
In our first paper (oral), we study how to use a NeRF-style representation to propagate physical properties of objects: Real-time Mapping of Physical Scene Properties with an Autonomous Robot Experimenter.
In our second paper, we introduce a method to execute simple skills (e.g. grasping and placing) in complex environments, whilst avoiding collisions with obstacles: Where To Start? Transferring Simple Skills to Complex Environments.
bottom of page