German Ros, Ph.D

I serve as Director of Simulation Ecosystem Development at Nvidia, helping Omniverse to grow and thrive. My passion is to create Embodied AI agents that can operate in the physical world at scale, showing intelligence, dexterity, and safe behaviors. In order to fulfill this goal, I focus on problems at the intersection of simulation, AI, and autonomy. I am a strong open-source advocate, and as part of my work I have led top-tier open-source projects such as the CARLA Autonomous Driving simulator, and the Open3D library.

Before joining Nvidia, I was the director of the Autonomous Agents Lab at Intel, in Santa Clara, California. I also served as a Research Scientist at the Toyota Research Institute (TRI), where I conducted research in the area of Simulation for Autonomous Driving, Scene Understanding, and Domain Adaptation, in the context of Autonomous Driving. I obtained my PhD in Computer Science at Autonomous University of Barcelona (2016), and the Computer Vision Center (CVC).

News

• [2024.06.14] Check out the results of the CARLA Autonomous Driving Challenge 2024 as part of the Autonomous Grand Challenge @ CVPR 2024 Workshop Foundation Models for Autonomous Systems.
• [2024.04.01] Our Photorealistic UrbanSyn dataset is now available on Hugging Face.
• [2024.03.16] Our new dataset on 3D Object Relighting is out. Check out the paper here.

Recent Talks

• [2024.03.14] Talk at Nvidia GTC 2024: Open-Source Autonomous Vehicle Simulation With CARLA.
• [2023.12.10] Talk at IEEE Standard Association Symposium on Autonomous Driving: “CARLA: An Open Simulation Framework and Platform for Autonomous Driving”
• [2023.10.01] Talk at IROS Workshop on Photorealistic Image and Environment Synthesis for Robotics*”.

Publications

You can find my articles on my Google Scholar profile.