Training a world-class cohort of researchers in the theory and practice of a new generation of Autonomous, Intelligent Machines and Systems.
Find out more about the breadth of our research below.
In these videos, our researchers explain some of the work they're involved with. You can also see a selection of Research Posters presented by our students at the annual CDT Meeting.
Goal-Conditioned End-to-End Visuomotor Control for Versatile Skill Primitives
Identifying Sources and Sinks in the Presence of Multiple Agents with Gaussian Process Vector Calcul
Identifying Sources and Sinks in the Presence of Multiple Agents with Gaussian Process Vector Calcul | Adam Derek Cobb, Richard Everett, Andrew Markham & Stephen Roberts
AIMS Students | Ed Wagstaff
Ed Wagstaff (2016 cohort) describes his research in Machine Learning. He specialises in reinforcement learning, and uses the lessons of mathematical probability to help systems navigate uncertainty.
Surface Edge Explorer (SEE): Planning Next Best Views Directly from 3D Observations
This video explains how the Surface Edge Explorer (SEE) plans views to obtain complete scene observations as efficiently as possible.
Research Posters 2019
Below are the research posters presented at the Annual CDT Meeting in October 2019.
Andreas Kirsch - BatchBALD Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning
Research Presentations 2019
Below are the research presentations presented at the Annual CDT Meeting in October 2019.
Research Posters 2018
Below are the research posters presented at the Annual CDT Meeting in November 2018.
Ada Alevzaki – Localisation and policy synthesis for underwater swarming autonomous vehicles with probabilistic guarantees about safe exploration and reachability requirements
Siddhant Gangapurwala – Generative Adversarial Imitation Learning for Quadrupedal Locomotion using Unstructured Expert Demonstrations
Research Posters 2017
Below are the research posters presented at the Annual CDT Meeting in October 2017.
Shuyu Lin – Gaussian Process Based Spatial Inference of Environmental Properties with Noisy Location Data