Junjie Tang

Experience a transformed embedded software development process, with AI agents that scan for new requirements, propose code changes and tests to meet the requirements, and CI pipelines with virtualized hardware environments to validate the changes.

In this chalk talk, discover how automotive companies can migrate cloud-native development platforms from the AWS global partition to the AWS China partition, based on the example of the successful deployment of an industry-leading autonomous driving (AD) platform to the AWS China partition.

Automakers collect hundreds of petabytes of drive data from vehicle test fleets for autonomous-driving and highly automated-driving feature development, but sometimes they do not log the exact scenarios ML engineers need to train models against corner cases.

Learn how to build an autonomous vehicle (AV) data lake using a provided reference architecture and recent field notes. See how to design and build an end-to-end scene detection pipeline using Spark on Amazon EMR and expose scene metadata via Amazon S3 and Amazon DynamoDB.

In this session, explore the AWS autonomous driving data lake reference architecture to learn how organizations manage the challenge of ingesting, transforming, labeling, and cataloging massive amounts of data to develop automated driving systems using Amazon EMR, Amazon S3, Amazon SageMaker Ground Truth, and more. See how BMW Group collects 1 billion+ km of anonymized perception data from its...