Munich Data Science meets BMW Welt

Hey! We're announcing our second meetup, joint event with BMW Welt. Come, grab a beer, meet your peers and learn about machine learning applied to automotive tasks. At this particular event we will listen to two amazing speakers: Tessa will tell us how to plan path for autonomous vehicle to avoid collisions with pedestrians and Alex will tell how he developed deep learning car recognition engine for Mercedes and pushed it to production

Tessa van der Heiden:

Tessa is a Software Engineer at BMW that started her PhD at the University of Amsterdam to develop methods that forecast the locations of road users. This is an essential component in autonomous driving, because not knowing where other cars/pedestrians/bikes will be, the car might be too late to avoid an accident.

Her first publication was a model (SafeCritic) that predicted a trajectory of all pedestrians in a scene, based on what and who they see. It was published at the British Machine Vision Conference (BMVC 2019).

Her current work is on planning a path for the autonomous vehicle. The primary goal is that the path is safe, that is, it avoids collisions with people. Almost equally as important is the path is socially compliant. Since, unnatural and annoying manoeuvres can result in unsafe scenarios because they cannot be interpreted by people well.

She will discuss the method called SCR, which stands for Socially Compliant Robot

Alexander Tselikov:

Alex Tselikov works as a lead data scientist for KI labs in Munich where he is responsible for building machine learning and data engineering products. Before that, he had been a senior data scientist at Veon (one of the biggest telco in Russia with 50 mlns subscribers) where he had focused on applying AI algorithms for credit scoring, customer churn analysis, fintech, chat-bots with neural networks and natural language processing. He had also been responsible for building and deploying large-scale machine learning pipelines into production environments. He holds his Ph.D. in data analysis from MSIU (Russia)

Format:
• We start at 18:30
• 2 talks, 45 min each
• You can come hungry and thirsty, snacks and beer will await you :)
• We speak English
• Photos could be made during event