Aidan Scannell

PhD Researcher | Bayesian Machine Learning for Control

Avatar

Aidan Scannell

PhD Researcher in Robotics and Autonomous Systems

Bristol Robotics Laboratory

University of Bristol

University of the West of England

Biography

Hello, my name is Aidan Scannell and I am an aspiring researcher with interests at the intersection of probabilistic machine learning and control theory. I grew up in North Yorkshire and graduated from the University of Bristol in 2016. I am now a PhD researcher under the supervision of Professor Arthur Richards and Dr Carl Henrik Ek focusing on data-efficient learning for the control of robotic systems (quadcopters). I am particularly interested in uncertainty quantification for learning-based control and as a result a lot of my work focuses on Bayesian non-parametric methods, specifically Gaussian processes and variational inference.

I am a real programmer that uses the butterfly effect to program.

Interests

  • Probabilistic modelling
  • Gaussian processes
  • Variational inference
  • Learning-based control
  • Optimal control
  • Robotics and autonomous systems

Education

  • PhD in Robotics and Autonomous Systems, 2021

    University of Bristol

  • MEng Mechanical Engineering, 2016

    University of Bristol

Blog Posts

One Keyboard to Rule Them All - I Built a Dactyl Manuform

After the first lockdown here in the UK, I decided that building a keyboard would make a good lockdown 2.0 project. I've had my eye on …

Creating a CV/Resume in Org-Mode using LaTeX Templates

Over the last few years I have been trying to find the best tools for managing my CV/resume. Previously I was maintaining a JSON file …

Experience

 
 
 
 
 

Teaching Assistant

University of Bristol

Sep 2018 – Present Bristol, UK
 
 
 
 
 

PhD Researcher

Bristol Robotics Laboratory - University of Bristol

Sep 2017 – Present Bristol, UK

My research is focused on data-efficient learning for the control of robotic systems. I am particularly interested in uncertainty quantification in model-based reinforcement learning and as a result a lot of my work focuses on Bayesian nonparametric methods, specifically Gaussian processes. EPSRC Centre for Doctoral Training in Future Autonomous and Robotic Systems (FARSCOPE).

Work to date:

  1. Identifiable Mixtures of Sparse Variational Gaussian Process Experts
  2. Trajectory Optimisation in Learned Multimodal Dynamical Systems

Recent Publications

Identifiable Mixtures of Sparse Variational Gaussian Process Experts

Mixture models are inherently unidentifiable as different combinations of component distributions and mixture weights can generate the …

Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE Collocation

Synergising Bayesian inference and Riemannian geometry for control in multimodal dynamical systems.

Recent & Upcoming Talks

Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE Collocation

In this talk I will present our ICRA 2021 paper “Trajectory Optimisation in Learned Multimodal Dynamical Systems via Latent-ODE …

Synergising Bayesian Inference and Probabilistic Geometries for Robotic Control

This talk presented recent work synergising Bayesian inference and probabilistic Riemannian geometries to control multimodal dynamical …

Projects

GPJax - Gaussian Processes in Jax

I am developing a minimal Python package for implementing Gaussian process models in Python using JAX. I have spent a lot of time using …

Trajectory Optimisation in Learned Multimodal Dynamical Systems

This work presents a two-stage method to perform trajectory optimisation in multimodal dynamical systems with unknown nonlinear …

Identifiable Mixtures of Sparse Variational Gaussian Process Experts

This work introduces a variational lower bound for the Mixture of Gaussian Process Experts model with a GP-based gating network based …

Approximate Inference

This work implements and compares a variety of approximate inference techniques for the tasks of image de-noising (restoration) and …

Model-Based Reinforcement Learning with Gaussian Processes

In this work I re-implemented the PILCO algorithm in python using Tensorflow and GPflow. This work was mainly carried out for personal …

Probabilistic Modelling

I am in the process of creating Jupyter notebooks for several probabilistic models (Bayesian linear regression, Gaussian process …

Uncertain Agentspeak

During the first (taught) year of the FARSCOPE CDT program I conducted my masters thesis under the supervision of Professor Weiru Liu …

Amazon Picking Challenge

As part of the FARSCOPE CDT program I worked in a team to develop a solution to Amazon’s picking challenge. This involved designing a …

Autonomous Vehicle Lane Detection Software

An application was designed following the model-view-controller architecture to enable multiple autonomous vehicle algorithms to be …

Kidnapped Robot

This project involved developing algorithms capable of localising a robot within a known environment but at an unknown position and …

Ultrasonic Non-Destructive Testing

This project entailed the design of an ultrasonic phased array for operation into the human body using Matlab.

UAV Swarm

This project involved developing distributed software enabling a swarm of fixed wing UAVs to track a pollutant cloud. A discrete time …

Contact