RAD - People

Faculty

Subramanian Ramamoorthy Professor and Personal Chair of Robot Learning and Autonomy	Michael Burke Visiting Faculty as Honorary Fellow (Lecturer, Monash University, Australia)
Research Staff

Longfei Chen	Alexandros Keros	Alejandro Bordallo
PhD students

Stefanie Speichert (Co-supervised with Prof Alex Lascarides)	George Kamaras (RAS CDT student)	Rimvydas Rubavicius (NLP CDT student, co-supervised with Prof Alex Lascarides)

Servinar Cheema	Jay Park (Co-supervised with Prof Alex Lascarides)	Jack Rome (Co-funded by Dyson; RAS CDT Affiliated student)

Peter D. Fagan (RAS CDT student)	Aditya Kamireddypalli

Alumni

Postdoctoral Research Associates

PhD students

Dr. Artūras Straižys (2024) - Learning robotic cutting of viscoelastic objects from demonstration using force sensing.
(First position after PhD: Senior Systems Engineer at Trig Avionics Ltd.)
Dr. Todor Davchev (2022) - Structured machine learning models for robustness against different factors of variability in robot control
(First Position after PhD: Research Scientist at DeepMind)
Dr. Martin Asenov (2022) - Architectures for online simulation-based inference applied to robot motion planning
(First Position after PhD: Machine Learning Engineer at Hyperscience)
Dr. Daniel Angelov (2021) - Composing diverse policies for long horizon tasks
(First Position after PhD: Co-founder and CTO at Efemarai)
Dr. Emmanuel Kahembwe (2021) - Efficient methods and architectures for deep neural network sequence models
(First Position after PhD: CEO, VDE UK Ltd.)
Dr. Yordan Hristov (2021) - Interactive robot learning with human alignment
(First Position after PhD: Postdoctoral Research Associate, School of Informatics, University of Edinburgh - NPL Metrology Fellowship)
(Current Position: Postdoctoral Researcher, Facebook AI Applied Research)
Dr. Svetlin V Penkov (2019) - Learning structured task related abstractions
(First Position after PhD: Research Scientist at FiveAI)
(Current Position: Co-founder and CEO at Efemarai)
Dr. Pavlos Andreadis (2018) - Coarse Preferences: Representations, Elicitation, and Decision Making
(First Position after PhD: University Teacher in Informatics, University of Edinburgh)
(Current Position: Teacher in Informatics, The University of Edinburgh)
Dr. Alejandro Bordallo (2017) - Intention Prediction for Interactive Navigation in Distributed Robotic Systems
(First Position after PhD: Chief Robotics Officer at Robotical Ltd.)
(Current Position: Director of Motion Planning and Prediction, FiveAI)
Dr. Stefano Albrecht (2015) - Utilising policy types for effective ad hoc coordination in multiagent systems
(First Position after PhD: Postdoctoral Research Associate, Learning Agents Research Group (LARG), The University of Texas at Austin)
(Current Position: Lecturer, School of Informatics, University of Edinburgh)
Dr. Efstathios Vafeias (2015) - Recognising activities by jointly modelling actions and their effects
(First Position after PhD: Research Engineer, Toshiba Medical Visualization Systems Europe - Edinburgh) (Current Position: Machine Learning Enginer, Stripe)
Dr. Majd Hawasly (2014) - Policy space abstraction for a lifelong learning agent
(First Position after PhD: Research Fellow, School of Computing, The University of Leeds)
(Current Position: Senior Research Scientist, FiveAI)
Dr. Benjamin Rosman (2014) - Learning domain abstractions for long lived robots
(First Position after PhD: Research Scientist, Mobile Intelligent Autonomous Systems Group , The Council for Scientific and Industrial Research (CSIR) - South Africa)
(Current Position: Associate Professor, University of the Witwatersrand)
Dr. Aris Valtazanos (2013) - Decision shaping and strategy learning in multi-robot interactions
(First Position after PhD: Postdoctoral Research Associate, Institute for Language, Cognition and Computation , School of Informatics, The University of Edinburgh)
(Current Position: Chief Scientist, WovenLight)
Dr. Thomas Larkworthy (2012) - Motion planning for self-reconfiguring robots
(First Position after PhD: Postdoctoral Research Associate, Ocean Systems Laboratory, Heriot-Watt University)
(Current Position: Founder and self-employed, Ex-Firebase, Ex-Google Cloud)
Dr. Ioannis Havoutis (2012) - Motion planning and reactive control on learnt skill manifolds
(First Position after PhD: Postdoctoral Research Associate, Dept. of Advanced Robotics, Italian Institute of Technology)
(Current Position: Departmental Lecturer, Oxford Robotics Institute, University of Oxford)

MPhil students

Jack Geary (2021) - Resolving conflict in decision-making for autonomous driving

MSc by Research students

Quanyi Li (2023) - Full-sensor autonomous vehicle falsification via compositional adaptive sampling
Aditya Kamireddypalli (2021) - Physics based parameter estimation of deformable material using robotic indentation primitives
Carson Vogt (2015) - Wind flow sampling using an autonomous UAV

MSc students

Nathaniel Hey (2023) - Identification of highly boosted H–>yy decays with the ATLAS detector using deep neural networks
Ana Deligny (2022) - Learning to manipulate unknown objects with underactuated robots
Zhe Hua (2022) - Learning motion primitives from human tool-using behaviours
Cesar Ochoa (2022) - Evaluating the Vision Checklist in a clinical context
Sijie Li (2020) - Object classification using proprioceptive force and proximity information for upper limb prostheses
Nevena Blagoeva (2019) - Adversarial attacks in the closed loop settings of Deep Reinforcement Learning
Mounika Gurram (2019) - Vision-based surgical skill assessment in laproscopic training on eoSurgical simulator using deep learning
Katie Lu (2019) - Active viewpoint selection for 3D reconstruction with space carving
Qihao Shan (2019) - Improving motion plans using expert guided value functions
Arturas Straizys (2019) - Deformable object manipulation using force feedback
Mike Woodcock Calvache (2019) - Hierarchical Reinforcement Learning for robustness, performance and explainability
David A. Wagner (2018) - Policy interpretability via approximate influence functions
Adeel Mufti (2018) - Probabilistic model-based Reinforcement Learning using the Differentiable Neural Computer
Sumedh Ghaisas (2017) - Learning framework for general game playing
Jack Geary (2017) - Learning and interactive decision making for human-robot coordination
Martin Asenov (2017) - Active sensing of spatiotemporal phenomena with a UAV
Faiz Mirza (2017) - Visual prediction from active manipulation with a UR-10 robotic arm
Arnav Varma (2017) - Multi-camera array calibration and predictive camera selection
Daniel Angelov (2016) - Physical scene understanding through active manipulation
Tanya Soni (2016) - Multi-camera array calibration and predictive camera selection
Emmanuel M. Kahembwe (2015) - Planning coordinated actions with trajectory clusters
James Ganis (2015) - Parallel adaptive sampling for particle filters
Jorge Salamanca (2015) - Empirical evaluation of properties of a model for learning to interact
Alexandre Silva (2015) - Mobile manipulation with a Kuka YouBot
Federico Boniardi (2014) - Robot navigation in crowded environments
Svetlin Penkov (2014) - Event related potentials in the electroencephalogram for human-robot interaction [Informatics Class Prize for Top Performance in Neuroinformatics and Computational Neuroscience MSc by Research]
Kshitij Tiwari (2014) - Co-operative manipulation with robots
Demetris Kolanis (2013) - Learning to adapt robotic interfaces
Yu Li (2013) - Learning to adapt robotic interfaces
Aniket Sanyal (2013) - Categorizing behaviour profiles using topological data analysis
Stavros Gerakaris (2012) - A graph theoretical approach to coordination of ad hoc agent teams
Jaymin Daniel Mankowitz (2012) - BRISK-based visual landmark localisation using Nao humanoid robots
Andrew Robinson (2012) - Searching for evidence of phase transitions in problem solving in humans, MResthesis
Nikolaos Tsiogkas (2012) - Ad hoc multi-robot teams in dynamic environments
Zheng Wu (2012) - Pose tracking on the Nao robots
Stefano Albrecht (2011) - Comparison of multiagent learning algorithms in ad hoc teams
Jayant Bansal (2011) - Multi-robot control with topology specifications: An empirical study
Nicholas Birnie (2011) - Multiagent sequential decision making in nonstationary environments
Anthony Cruickshank (2011) - The behaviour of an artificial market with adaptive agents under different conditions
Alesis Novik (2011) - Regime switching models for markets
Andrew Robinson (2011) - Achievement of global shapes through local goals in reconfigurable robotics
Thomas Joyce (2010), Low level embodied mathematical cognition and the beginnings of representation (Co-supervised with Alison Pease and Alan Smaill)
Jonathan Millin (2010) - In search of structure: Unsupervised learning in foreign exchange
Sheng Qin (2010) - Regime switching portfolio allocation algorithm
Alex Svanevik (2010), The role of metaphor and embodiment in the development of mathematical concepts: A computational approach (Co-supervised with Alison Pease and Alan Smaill)
[Informatics Prize for Outstanding MSc Project]
Efstathios Vafeias (2010) - Where is my humanoid? Vision-based localization
Benjamin Saul Rosman (2009) - Game theoretic procedures for learning structured strategies from demonstration
[Jim Howe Prize for Outstanding MSc (Artificial Intelligence) Student]
Richard Clossick (2008) - Learning a template based running strategy for a humanoid robot
Thomas George Elder (2008) - Creating algorithmic traders with hierarchical reinforcement learning
[Informatics Prize for Outstanding MSc (Computer Science) Student]
Sandhya Prabhakaran (2008) - Multi-scale, reactive motion planning with deformable linear objects
Short video describing this work.

UG/MInf students

Matthew Whyte (2022) - Perception-based control for aggressive driving in formula student competition
Frazer McIntosh (2018) - Recording a 3D scene using a mobile device and making measurements on recorded features
Nantas Nardelli (2016) - StarCraft: Brood War as an agent learning platform
Paul Harris (2015) - A gesture-based interface for exploring simulations in virtual reality
Borislav Ikonomov (2015) - Brain-computer interface for modulating human-robot interaction
Peter MacGregor (2015) - Calibration-free brain-computer interface
Moataz Elmasry (2014) - A study of trading agents for TAC Ad Exchange
Jack Pimbert (2014) - A multiagent poker player for No Limit Texas Holdem
Christian Pelissier (2013) - A No Limit Texas Hold'em agent emphasizing individual player exploitation
Flavius Popescu (2013) - Coordination mechanisms for multi-robot systems in uncertain environments
Sean Wilson (2013) - Learning to improve kicking motions on the Nao robot
Petar Valentinov Ivanov (2012) - Self-localization using Extended Kalman Filter and Multi-hypothesis EKF
Seyed Behzad Tabibian (2012) - Games robots play: Coordination mechanisms for multi-robot systems in uncertain environments
Daniel Wren (2012) - Automatic colour calibration using multiple views
Georgi Gochev (2011) - Skill learning from interactions with multiple opponents
Seyed Mohammadali Eslami (2009) - Evolving robust control strategies for a simulated robot
[Jim Howe Prize (AI UG) and B.Eng.(AI & SE) Class Medal]
Jay Kotak (2009) - Visual tracking and data acquisition system for team sports

Visitors

Dr. Esra Erdem (2019) - SICSA Distinguished Visiting Fellow
(on sabbatical from Faculty of Engineering and Natural Sciences, Sabanci University, Turkey)
Dr. Volkan Patoğlu (2019) - Visiting Fellow
(on sabbatical from Faculty of Engineering and Natural Sciences, Sabanci University, Turkey)
Daniel Zwilling (2015) - Multi-robot motion planning with YouBots
(from FH Aachen - Aachen University of Applied Sciences)
Fabio Previtali (2014) - Distributed sensor network for multi-robot surveillance
(from Dipartimento di Informatica e Sistemistica, Sapienza Università di Roma)
Gwendolijn Schropp (2013/14) - Behaviour modelling and plan recognition for ad hoc player/coach in RoboCup SPL (MSc research student from Information and Computing Sciences, Utrecht University)
Dr. Matteo Leonetti (2010 - 2012) - Planning and learning in non-Markovian domains
(from Dipartimento di Informatica e Sistemistica, Sapienza Università di Roma)
Thomas McGuire (2010/11) - Real time vision and localization for the Nao humanoid robot
(from Universität Siegen, Germany)