Matt joined ORI in 2020 as a member of Pembroke College. As a DPhil student in the GOALS Lab he is supervised by Prof. Nick Hawes. His research interests cover model based sequential decision making, focusing particularly on meta-reasoning and Bayesian RL.
Matt completed his MEng in Engineering Science in 2020, also at Oxford. Having worked for a year as an embedded software engineer before university, he is comfortable anywhere along the line from high-level planners to assembly routines. Throughout his time at Oxford he has led the ORI's RoboCup Manipulation sub-team, led a team of undergraduate robot designers, and presented beam instrumentation design research at CERN in Geneva.
Outside of the DPhil, Matt enjoys indoor (reading, rock climbing/bouldering) and outdoor (swimming, hiking) pursuits as well as building arguably useful gadgets.
Most Recent Publications
Planning under uncertainty for safe robot exploration using Gaussian process prediction
Planning under uncertainty for safe robot exploration using Gaussian process prediction
Probabilistic planning for AUV data harvesting from smart underwater sensor networks
Probabilistic planning for AUV data harvesting from smart underwater sensor networks
Bayesian reinforcement learning for single-episode missions in partially unknown environments
Bayesian reinforcement learning for single-episode missions in partially unknown environments
Markov decision processes with unknown state feature values for safe exploration using Gaussian processes
Markov decision processes with unknown state feature values for safe exploration using Gaussian processes
Stop! Planner Time: Metareasoning for Probabilistic Planning Using Learned Performance Profiles
Stop! Planner Time: Metareasoning for Probabilistic Planning Using Learned Performance Profiles