Transforming Automotive Infotainment with Data
summary
Rivian builds its infotainment analytics stack from scratch and collects de‑identified events from a roughly 90k vehicles fleet via a proprietary vehicle‑to‑cloud transport over LTE/Wi‑Fi, using a Kotlin event library, Kafka, dbt and Databricks with a Medallion bronze/silver/gold pipeline. Monthly OTA updates enable versioned A/B ambitions, privacy is enforced by limiting raw data access, and a concrete product born from fleet telemetry is a charging site reliability score used by navigation to prefer dependable chargers.
AI-written summary · about
chapters (15)
- 0:00Introduction
- 1:33Rivan’s mission
- 2:57Software-defined vehicles
- 4:00Building infotainment
- 6:06User feedback needs
- 7:09Privacy-first analytics
- 10:00Automotive data complexity
- 12:27Scalable data collection
- 14:58Raw data to insights
- 18:35Navigation engagement trends
- 20:46Software-defined benefits
- 21:49Q&A
- 24:41Data-driven features
- 26:47Data pipeline tech
- 27:52Closing remarks
related talks
24mCreating a Data Platform for Software-Defined Electric Vehicles
35mReal-time analytics at IoT scale
05mPivot
27mData-driven and cloud-native ecosystems in the automotive industry
17mLightning Talk: PIVOT: An Open Community Platform for Sharing Vehicle Telem...
30mEnabling data-driven development for autonomous driving at BMW
16mTransforming Analytics With AI: A Comprehensive Guide to an Advanced Tech Stack
17mFrom Stock Optimization to Digital Vehicle Twin with VW