Autonomous Mobility

Accelerate autonomous vehicle development with purpose-built AWS and partner services and solutions

AWS is powering the continued advancement of Autonomous Vehicle (AV) development.
Developing and deploying Advanced Driver-Assistance Systems (ADAS) and AV Systems requires a development platform with highly scalable compute, storage, networking, as well analytics and deep learning frameworks. This platform requires capabilities that allow for the collection, ingestion, storage, processing and analytics, labeling and annotation, map development, algorithm and model development, simulations, verification and validation, and workspace management functions (inclusive of MLOps and DevOps). Leading automotive customers turn to AWS as their ADAS/AV development platform for our breadth and depth of managed services, solutions, experience, and partner community to deliver the architecture and technology required for to develop safe, reliable, and cost-optimized autonomous and ADAS systems.


Unmatched compute storage and network scale
AWS solves petabyte-scale data processing, storage, and management needs by delivering thousands of cores of compute for development and validation.
Accelerate time to market
Building on AWS helps customers optimize their software engineering to be more agile, reducing development and validation costs and supporting a faster time to market.
Multiple ways to control cost
AWS has the most classes of storage of any cloud resulting in increased cost efficiency because data can be configured and paid for based on the frequency of access, durability, and availability requirements.

Autonomous Mobility use cases and solutions

Explore solutions by use case

Data Management, Processing & Analytics

These solutions give companies a flexible and scalable data flywheel, in which categorized data continues to feed workloads that become increasingly iterative with each stage, optimizing model development, simulation, testing, and validation.

Learn more »

Model & Algorithm Development

Build powerful solutions to facilitate critical self-driving functions, including lane-keeping assist, adaptive cruise control, and automated emergency braking, accelerating their time to market.

Learn more »

Autonomous Vehicle Software Development

Streamline development within global devops teams, increase efficiency, expand test coverage, all while reducing costs and accelerating time to market.

Learn more »

Data Labeling & Anonymization

Cost-effectively manage data labeling and anonymization in the AWS cloud through improved automation, tools, and workflows.

Learn more »

Simulation & Verification

Increase overall test coverage by using raw and synthetic data supported by software-in-loop and hardware-in-loop simulation workloads.

Learn more »

Data Collection, Ingestion & Enrichment

Run campaigns for an operational design domain (ODD) such as lane-keeping assistance systems (LKAS) and automated emergency braking (AEB) to develop models and algorithms for autonomous driving and cloud validation.

Learn more »

Autonomous Driving Data Framework (ADDF)

Scale and accelerate ADAS and autonomous driving development using the data processing pipelines, visualization mechanisms, analytics interfaces, and a scene search interface.

Learn more »

Weights and Biases for AWS

Weights & Biases is the leading developer-first MLOps platform to build better models faster. Weights & Biases lets ML teams track experiments, understand model and dataset dependencies, visualize and understand their datasets, and collaborate and share findings. 

Learn more »

Get started with select AWS services

Amazon EC2 T4g instances are powered by Arm-based AWS Graviton2 processors. T4g instances are the next generation low cost burstable general purpose instance type that provide a baseline level of CPU performance with the ability to burst CPU usage at any time for as long as required.
Amazon EC2 Inf1 instances deliver high-performance ML inference at the lowest cost in the cloud.
Amazon EC2 P4d instances deliver the highest performance for ML training and high performance computing (HPC) applications in the cloud.
Amazon EC2 P3 instances deliver high performance compute in the cloud with up to 8 NVIDIA® V100 Tensor Core GPUs and up to 100 Gbps of networking throughput for machine learning and HPC applications.
Amazon SageMaker helps data scientists and developers to prepare, build, train, and deploy high-quality ML models quickly by bringing together a broad set of capabilities purpose-built for ML.
Amazon SageMaker Ground Truth is a fully managed data labeling service that makes it easy to build highly accurate training datasets for machine learning.
Amazon SageMaker Ground Truth Plus helps you to create high-quality training datasets without having to build labeling applications or manage a labeling workforce.
AWS Wavelength embeds AWS compute and storage services within 5G networks, providing mobile edge computing infrastructure for developing, deploying, and scaling ultra-low-latency applications.
AWS Snowcone is the smallest member of the AWS Snow Family of edge computing, edge storage, and data transfer devices.
AWS IoT FleetWise makes it easier for you to collect, transform, and transfer vehicle data to the cloud in near real time and use that data to improve vehicle quality, safety, and autonomy.

Customer stories

Learn how leading automotive companies are transforming their businesses with AWS Autonomous Mobility solutions.

Torc logo

Transforming Autonomous Trucking with a Data Lake Built on Amazon S3

Learn about key insights from Torc Robotics after migrating to a modern data lake in the cloud with Amazon S3.



Read the blog >>
Torc Robotics Transforms Autonomous Trucking with a Data Lake Built on Amazon S3
Mobileye icon

Mobileye: Navigating the winding road toward driverless mobility

Autonomous vehicles (AVs) are becoming a reality, as evidenced by the variety of advanced driver assistance systems (ADAS) and growing number of AV test programs on the road. Mobileye, a global leader in the development of technologies for ADAS and autonomous driving solutions, has been an integral part of this technology revolution.

Watch the video »
Navigating the winding road toward driverless mobility (56:41)
Lyft Level 5 logo

Lyft Increases Simulation Capacity, Lowers Costs Using Amazon EC2 Spot Instances

Lyft increased simulation capacity and lowered costs using Amazon EC2 spot instances to improve performance and safety of its self-driving system.

Read the case study »

Toyota Research Institute logo

Toyota Research Institute accelerates safe automated driving with deep learning at a global scale on AWS

Toyota Research Institute uses Amazon EC2 P3 instances to efficiently handle and process the huge amount of data it collects, helping accelerate development of its automated driving systems.

Read the blog »

Momenta logo

Momenta Accelerates Autonomous Driving Technology with AWS

Momenta uses AWS storage and IoT solutions to collect and process hundreds of petabytes of data from on-board sensors of its autonomous vehicles.

Read the case study »

WeRide logo

WeRide Speeds Autonomous Driving Machine Learning Model Training from Weeks to 12 Hours on AWS

WeRide sped its autonomous driving machine learning model training from weeks to 12 hours on AWS.

Read the case study »

TuSimple logo

Building TuSimple's Level 4 Autonomous Driving Truck Using AWS

TuSimple has simulated billions of miles driving and developed its autonomous driving platform that uses sophisticated deep learning algorithms on AWS.

Watch the video »

Innovate with key industry partners

Engage with a global community of AWS Partners who have demonstrated technical expertise and customer success in building solutions on AWS.


Check out AWS Automotive blog posts, videos, podcasts, and other resources to learn more and stay up to date on the latest developments.

Featured resource

Autonomous Development Ebook

Autonomous vehicles hold the promise of a safe, efficient, and accessible future that will minimize the dependency on—and eventually eliminate—the need for a human driver. Read this ebook to learn how Toyota Research, Lyft, Momenta, and TuSimple accelerate their autonomous driving system development by building on AWS.

Building an automated scene detection pipeline for autonomous driving thumbnail

Building an automated scene detection pipeline for Autonomous Driving – ADAS Workflow

This Field Notes blog post in 2020 explains how to build an Autonomous Driving Data Lake using this Reference Architecture.

Read the blog »

stock image autonomous cars on highway

How Autonomous Trucking Became the Unlikely Hero of Autonomous Vehicle Development

Class 8 commercial trucks, the tractor trailers you pass every day on the highway, typically log astronomical mileages on long routes with relatively predictable conditions. That’s an ideal environment for developing and proving self-driving technology.

Read the blog »

Simulation in AWS RoboMaker thumbnail

Run any high-fidelity simulation in AWS RoboMaker with GPU and container support

To support high fidelity simulation, AWS RoboMaker now supports GPU-based simulation jobs designed for compute intensive workflows, such has high-fidelity simulation.

Read the blog »

ROS Bag Data on AWS using rviz and Webviz thumbnail

Deploy and Visualize ROS Bag Data on AWS using rviz and Webviz for Autonomous Driving

This blog post describes three solutions on how to deploy and visualize ROS bag data on AWS by using two popular visualization tools.

Read the blog »

video labeling in Amazon SageMaker Ground Truth

Label Videos with Amazon SageMaker Ground Truth

As models become more sophisticated, AWS customers are increasingly applying machine learning prediction to video content. Autonomous driving is perhaps the most well-known use case, as safety demands that road conditions and moving objects be correctly detected and tracked in real time.

Read the blog »

3D point cloud labeling thumbnail

Label 3D Point Clouds with Amazon SageMaker Ground Truth

Using the built-in graphical user interface (GUI) and its shortcuts for navigation and labeling, workers can quickly and accurately apply labels, boxes and categories to 3D objects (“car,” “pedestrian,” and so on).

Read the blog »

Related resource

Capgemini Driving Automation System Validation

Helps OEMs rapidly adopt the underlying architecture and technologies of autonomous driving.

Learn more »

Related resource

DXC and AWS Robotic Drive Cloud

Provides the tools, services, and base backend platform on AWS to accelerate the build of autonomous driving functions and software by enriching AWS services optimized for autonomous driving-specific workloads.

Learn more »

Get started

Automotive companies of all types and sizes—from global automakers to startups—rely on AWS. Contact our experts and start your own journey to the cloud today.