Adam
Scibior
CTO & Co-Founder
Inverted AI
Adam Ścibior has a diverse work experience. Adam started as a Research Intern at Microsoft in 2015. In 2019, they became a Postdoctoral Research Fellow at The University of British Columbia. During the same year, they also co-founded Inverted AI and served as the Chief Technology Officer. Currently, they are an Adjunct Professor at The University of British Columbia, starting in 2022. Adam Ścibior has a strong educational background in the field of machine learning. Adam obtained their Doctor of Philosophy (Ph.D.) in Machine Learning from the University of Cambridge, where they studied from 2014 to 2019. Prior to that, they completed their Bachelor's Degree in Computer Science at the same university from 2011 to 2014. In addition to their studies at the University of Cambridge, Adam also pursued a Master's Degree in Physics from Uniwersytet im. Adama Mickiewicza w Poznaniu between 2012 and 2014, after completing their Bachelor's Degree in Physics at the same university from 2010 to 2012. During their doctoral studies, Adam also had the opportunity to be a part of the Max Planck Institute for Intelligent Systems, where they continued their research in Machine Learning.
17 April 2024 11:00 - 11:30
Generating realistic human behaviors in AV simulations
Simulation is a key component of validating the safety of autonomous vehicles, gradually replacing expensive on-road tests. The main limitation to its applicability is the domain gap between the real world and the simulated one, and numerous advances in both classical simulation methods and generative AI are gradually reducing this gap in terms of dynamics, visuals, sensor physics and content. In this talk, Adam will outline Inverted AI’s efforts in bridging the remaining behavioral gap, that is how the actions of simulated humans differ from the actions of real humans. He will discuss the key difficulties faced by existing approaches and how to build a better solution, including where to find suitable data, what architectures to use, how to connect them to existing workflows, and what it means for the future of AV development.