Postdoctoral researcher | Machine learning | Sequential decision making | Robotics
Hello, my name is Aidan Scannell and I am a postdoctoral researcher with interests at the intersection of machine learning, sequential decision making and robotics. My research aims at enabling autonomous agents to learn behaviours, such that they can learn to solve any task. I am particularly interested in controlling agents with natural language instructions and the challenges associated with developing a robotic foundation model which can generalise across tasks, objects and embodiments.
I am a Finnish Center for Artificial Intelligence postdoctoral researcher at Aalto University in Joni Pajarinen’s Robot Learning Lab and Arno Solin’s Machine Learning Research Group. I obtained my PhD from the University of Bristol under the supervision of Arthur Richards and Carl Henrik Ek. During my PhD I developed methods for controlling quadcopters in uncertain environments by synergising methods from probabilistic machine learning, stochastic differential geometry and reinforcement learning.
PhD Robotics and Autonomous Systems, 2022
University of Bristol, UK
MEng Mechanical Engineering, 2016
University of Bristol, UK
[05.04.24] New paper accepted to L4DC 2024 - Residual Learning and Context Encoding for Adaptive Offline-to-Online Reinforcement Learning
[16.02.24] New paper accepted to ICLR 2024 - Function-space Prameterization of Neural Networks for Sequential Learning
[03.10.23] Giving a talk on "(Function-space) Laplace approximation for Bayesian neural networks" to the NSF safe RL team.
[03.08.23] Presenting our work on “Neural Networks as Sparse Gaussian Processes for Sequential Learning” at the International Workshop of Intelligent Autonomous Learning Systems 2023.
[22.06.23] New paper accepted to the Duality Principles for Modern Machine Learning ICML 2023 Workshop - Sparse Function-Space Representation of Neural Networks.
This project seeks to evaluate and compare different approaches for learning dynamics models in model-based RL. In particular, we plan to compare different approximate inference techniques (e.g. Laplace approximation, MC dropout, variational inference), as well as ensemble methods, to understand why they either succeed or fail in different environments.
This work presents a learning-based control method for navigating to a target state in unknown, or partially unknown, multimodal dynamical systems. In particular, it develops a model-based reinforcement learning algorithm that can remain in a desired dynamics mode with high probability. For example, if some of the dynamics modes are believed to be inoperable.
This work presents a two-stage method to perform trajectory optimisation in multimodal dynamical systems with unknown nonlinear stochastic transition dynamics. The method finds trajectories that remain in a preferred dynamics mode where possible and in regions of the transition dynamics model that have been observed and can be predicted confidently.
During the first (taught) year of the FARSCOPE CDT program I conducted my masters thesis under the supervision of Professor Weiru Liu and Dr Kevin McAreavey titled “Extending BDI Agents to Model and Reason with Uncertainty”. I implemented and extended the AgentSpeak(L) (agent-based programing) language to enable agents to model and reason with uncertainty in a computationally efficient manner.
An application was designed following the model-view-controller architecture to enable multiple autonomous vehicle algorithms to be simulated in different views and to allow the input parameters to be altered in run time e.g. adaptive threshold parameters, coordinates for inverse perspective mapping, number of sample points etc. The code will run slower due to the MVC architecture.