-
AWS Solution: Scene Intelligence with Rosbag on AWS
Extract, process, and index driving scenarios from rosbag sensor data with automated object and lane detection. Enables autonomous driving teams to search and query specific scenes across massive datasets for ML model training, validation, and simulation.
-
Scaling Automated Driving data processing and data management with BMW Group on AWS
How BMW Group organizes and pre-processes petabytes of vehicle sensor data on AWS. Uses Amazon S3, ML pipelines, and analytics services to collect, analyze, and visualize driving data at scale — accelerating the development and validation of automated driving functions.
-
How Continental uses Mountpoint for Amazon S3 in autonomous driving development – accelerating simulation performance by 20%
Replace complex caching and prefetching logic with Mountpoint for Amazon S3 to simplify Continental's simulation architecture. By mounting S3 buckets as local file systems, simulation workloads access petabytes of driving data directly, boosting throughput by 20% while reducing operational complexity.
-
Guidance for Autonomous Driving Data Framework on AWS
Modular, reusable framework for building autonomous driving data pipelines on AWS. Provides customizable modules covering the full lifecycle — from data ingestion and labeling to scenario search, simulation, and analytics — following AWS Well-Architected best practices.
-
Autonomous Driving Data Framework (ADDF) security and operations guide
Best practices for securing ADDF deployments on AWS — covering IAM policies, network isolation, encryption at rest and in transit, CI/CD pipeline hardening, and operational monitoring. Helps DevOps and security teams confidently deploy autonomous driving workloads in production.