Edge to Core to Cloud data pipelines for Autonomous vehicles

Building Software Defined Cars / Autonomous vehicles are hard. Every neural net in the software stack needs to handle 1000’s of conditions and geolocations. Several aspects become important for a successful AV platform, however on the forefront are – safety, availability to tons of data, inference on the edge and reproducibility.

Safety is a non-compromisable primary objective and needs models tested on huge datasets to be confident as well as faster iterations in producing well tested models.

Tons of data Collecting enormous amounts of data under innumerable scenarios is key to building good AV models. This data needs to be labeled, accessible and managed over its lifecycle.

Inferencing on the edge -  Inferencing running on the AV vehicle is typically limited in its hardware capabilities. Hence iterating on finding the right model without losing performance, a needs access to tons of data.

Reproducibility is important, with proper version control of datasets, models and experimentation, to understand why a model behaved a certain way.
 
Data and accessibility to tons of data, is at the cornerstone of building a production grade AV platform.Learn the challenges and solutions to building at scale Autonomous vehicle data pipelines, in this session.

Shailesh is responsible for CloudFabrix's Product vision, Marketing, and strategy for Data Observability and AIOps market. CloudFabrix is a Data Intelligence and Automation company. Shailesh is focused on evangelizing and extending the use cases for transformative "Robotic Data Automation Fabric" to unify Observability, AIOps and Automation across the edge and cloud.