How to Run Millions of Self-Driving Car Simulations on GCP (Cloud Next '19)

Опубликовано 12 апреля 2019, 0:06

Cruise Automation is a leading developer of autonomous vehicle technology. In this session, we will dive into the infrastructure which allows us to run hundreds of thousands of autonomous simulations every day and analyze the results quickly and efficiently. Cruise runs the vast majority of our testing on Google Cloud, taking advantage of high scalability of compute and GPU resources for our diverse workloads.

Our simulation frameworks allow us to replay data gathered from road testing or generate complex variations on human-defined scenarios. We will take a look at the technology and infrastructure behind these frameworks, challenges scheduling and scaling our workload on GCP, complexities accessing high-definition 3D maps and other resources required to run each simulation, and our data pipeline which allows engineers to quickly instrument and analyze their results.

Build with Google Cloud → bit.ly/2KbTers

Watch more:
Next '19 Compute Sessions here → bit.ly/Next19Compute
Next ‘19 All Sessions playlist → bit.ly/Next19AllSessions

Subscribe to the GCP Channel → bit.ly/GCloudPlatform

Speaker(s): Adrian Macneil

Session ID: CMP207
product: Cloud - General; fullname: Adrian Macneil; event: Google Cloud Next 2019;