I am a postdoc at the Visual Intelligence for Transportation (VITA) lab at EPFL in Switzerland where I conduct research in computer vision for self-driving cars and robots that share a common space with people. Current projects are in perception, prediction and planning and include projects that use monocular depth (MonoLoco, ICCV2019), human pose estimation (PifPaf, CVPR2019), reinforcement learning to navigate a crowded space (Crowd-Robot Interaction, ICRA2019), new ideas for the Social Force model (STRC2019, hEART2019) and human path prediction in the context of self-driving cars.

Monoloco example
MonoLoco: Monocular 3D Pedestrian Localization and Uncertainty Estimation.

Presented at ICCV2019 in Seoul.
OpenPifPaf example
PifPaf: Composite Fields for Human Pose Estimation.

Presented at CVPR2019 in Los Angeles.
CrowdNav illustration
Crowd-Robot Interaction: Crowd-aware Robot Navigation with Attention-based Deep Reinforcement Learning.

Presented at ICRA2019 in Montreal.

Before returning to academia, I was the Senior Data Scientist at Sidewalk Labs (Alphabet) in New York City where I focused on machine learning for urban environments. My background is in particle physics where I hold a PhD from NYU and where I worked with Kyle Cranmer on physics and statistical analyses for ATLAS at CERN. I was on the core team that discovered the Higgs boson and the first person to see the 5σ threshold crossed.

Me elsewhere: Google Scholar   GitHub   Twitter   LinkedIn
Email: me@svenkreiss.com