Efimia Panagiotaki

I am currently a final year DPhil (PhD) student at the Mobile Robotics Group and the Cognitive Robotics Group of the Oxford Robotics Institute, University of Oxford, supervised by Dr Daniele De Martini and Prof Lars Kunze. My DPhil is funded by Google DeepMind through the Department of Engineering Science. During my studies, I am working part-time at OXA as Senior ML Engineer (Reasoning), at the Office of the CTO, Prof Paul Newman.

Before starting my DPhil I was working as the Lead Self-Driving Software Engineer at StreetDrone Ltd and was responsible for the software development of a prototype self-driving truck for a 5G-enabled CAL project in the Nissan factory, part of the 5G Create Scheme. Prior to that, I was working as Software Engineer (June 2018-2020) at StreetDrone Ltd and developed a full-stack self-driving software for the Nissan ENV200 and Renault Twizy for the SMLL Urban AV Trials, CCAV and Innovate UK project. I also worked as Data Processing Engineer at Williams Racing, Formula 1 team.

I finished my diploma (5-years Integrated BEng and MEng degree) in 2017 at the National Technical University of Athens in Athens, Greece, department of Electrical and Computer Engineering. During my studies, I spent 8 months at ETH Zürich conducting my master’s thesis at the Computer Vision Lab under the supervision of Prof Luc Van Gool and Dr Dengxin Dai, working with the AMZ Driverless Formula Student Team.

Inspired by the significant unknowns of real-world robot deployment, I am investigating the topics of representation learning and scene understanding for ground robotics applications.

Keywords: 3D spatial robotic perception, representation learning, scene understanding, graph structures/graph neural networks, vision-language models, multimodal semantic localisation, neural execution of graph algorithms, learning by abstraction, and explainable AI.

Always happy to connect and start new collaborations!