SHARE

Aurora Taps AWS for ML and Self-Driving Simulations

SEATTLE — Aurora, a provider of self-driving vehicle technology, selected Amazon Web Services (AWS) as its “preferred” cloud provider. Aurora’s relationship with AWS is intended to help Aurora with machine learning (ML) training and cloud-based simulation workloads, according to AWS last month. Aurora uses AWS’s infrastructure and capabilities, including high-performance computing, storage, and cybersecurity, to […]

Written By

Chris Ehrlich

Jan 18, 2022

Datamation content and product recommendations are editorially independent. We may make money when you click on links to our partners. Learn More

SEATTLE — Aurora, a provider of self-driving vehicle technology, selected Amazon Web Services (AWS) as its “preferred” cloud provider.

Aurora’s relationship with AWS is intended to help Aurora with machine learning (ML) training and cloud-based simulation workloads, according to AWS last month.

Aurora uses AWS’s infrastructure and capabilities, including high-performance computing, storage, and cybersecurity, to “safely accelerate” the development of Aurora Driver, its scalable self-driving vehicle technology.

Aurora Driver consists of sensors that perceive the environment, software that plans a path, and a computer that powers and integrates Aurora’s hardware and software with any vehicle platform.

Aurora uses the cloud to “process trillions of data points each day.” The company is scaling its training workloads in the cloud to complete up to 12 million physics-based driving simulations per day by the end of the year. The simulations build on the petabytes of data it collects during real-world road tests. Aurora has been running simulations at scale on AWS since 2019.

Before developing simulations, Aurora uses AWS to store and process the petabytes of data it logs during real-world testing and then train its ML models on that data. The pre-processing workloads run on Amazon Elastic Kubernetes Service (EKS) and Amazon EMR, a service for processing vast amounts of data in the cloud with open-source tools. Aurora’s ML training workloads use AWS-optimized deep learning frameworks, such as TensorFlow and PyTorch. Aurora orchestrates and auto-scales its simulation workflows over hundreds of thousands of concurrent vCPUs and thousands of concurrent GPUs with Amazon EKS and Amazon EC2.

The offline components of the Aurora Driver software stack run on AWS, including the Virtual Testing Suite, high-definition road maps, ML models, and software development tools. For example, Aurora uses Amazon SageMaker, a service to build ML models, and Amazon Elastic Compute Cloud (EC2) to enable its driving simulations.

“AWS’s highly scalable compute, machine learning, and analytics services are helping Aurora move self-driving vehicle technology forward, toward broad real-world use,” said Swami Sivasubramanian, VP of machine learning, AWS.

“We are proud to support the acceleration of autonomous vehicle innovation and look forward to the improved safety and efficiency the transformation of trucking, delivery, and mobility will allow.”

Chris Urmson, the CEO of Aurora, said the company’s advanced machine learning and simulation at scale are “foundational to developing our technology safely and quickly, and AWS delivers the high performance we need to maintain our progress.”

Chris Ehrlich

Chris Ehrlich is the managing editor of several web properties in the TechnologyAdvice network. He has over 20 years of experience delivering content-based results across journalism and communications, including on B2B technologies. As a leader in digital journalism, he’s driven targeted content that resonates with audiences and increases key metrics. As a leader in branded communications, he’s driven multi-channel content for clients that spreads their messages and generates measurable returns. He holds a B.A. in English and political science from Denison University in Ohio.

Aurora Taps AWS for ML and Self-Driving Simulations

Chris Ehrlich

Recommended for you...

Company

Categories