About me
I am currently an Entrepreneur in Residence at Antler in the autumn cohort 2024, in London. I am exploring opportunities at the intersection of AI and healthcare. In particular, my co-founder and I are developing a solution for automating compliance for R&D teams such that they can focus on innovation. We are building an AI Regulatory Expert that can work side by side with the development team, automatically discover evidence, generate regulatory documentation and identify any compliance issues. Stay tuned for more updates on our progress!
Previously, I was Lead Research Scientist at FiveAI. I led the Motion Planning and Prediction Applied Research team in tackling a variety of research and engineering challenges, such as robustifying planners, multi-agent interactions, integrating prediction into planning, etc. I explored hybrid combinations of machine learning (deep learning, reinforcement learning) with classical approaches such as Monte Carlo methods, Bayesian inference and Game Theory algorithms. The safety critical nature of the application meant that the solutions had to handle a large degree of uncertainty, generalise to novel situations and constrain the amount of risk when interacting with other human traffic participants.
In my final year at Bosch, I expanded my interests to Perception where we developed algorithms for HD Map Reconstruction from raw sensor data. Storing and keeping HD Maps updated is an expensive and non-trivial task despite the clear evidence of benefits for downstream tasks such as Planning and Perception. Utilising the recent advances in Machine Learning and Computer Vision, we implemented solutions for both Online usage on the vehicle and for Autolabeling the large amounts of data gathered by the self-driving vehicles. Me and my team were positioned at the intersection of Engineering and Research forming a link between the Level 4 self-driving team, Bosch Research and academia.
Before moving to industry, I completed a PhD within the ILCC institute of the School of Informatics at the University of Edinburgh under the supervision of Alex Lascarides and Subramanian Ramamoorthy.
Research interests
- Machine Learning: (Multi-agent) Reinforcement Learning, Imitation Learning, Deep Learning, Bayesian Methods
- Prediction, Planning and Decision Making
- Computer Vision (Perception in AD)
- Multi-agent Systems and Game Theory
Education
- PhD Informatics. Low-resource learning in complex games, School of Informatics, University of Edinburgh, 2018
- BSc (Hons) Robotics with Artificial Intelligence, University of Bradford, 2013 (1st class);
Awards
- Received Best student Overall Performance Award, University of Bradford, 2013
- Received Best Student Paper Award for “Exploiting action categories in learning complex games”, 2017