> Markdown version of [/videos/61-how-machine-learning-is-turning-the-automotive-industry-upside-down](https://www.wearedevelopers.com/videos/61-how-machine-learning-is-turning-the-automotive-industry-upside-down). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# How Machine Learning is turning the Automotive Industry upside down

How do you process ten terabytes of edge vehicle data daily? Discover why the automotive industry's future depends on scalable, safety-critical machine learning architectures.

- **Speakers:** Jan Zawadzki
- **Event:** WeAreDevelopers LIVE
- **Published:** November 5, 2020
- **Duration:** 26:55
- **URL:** https://www.wearedevelopers.com/videos/61-how-machine-learning-is-turning-the-automotive-industry-upside-down

## Summary

The automotive industry, a massive driver of global economics, faces flattening traditional vehicle sales alongside surging demand for scalable mobility. To adapt, manufacturers are leveraging machine learning to redefine business value. This transformation relies on the "virtuous cycle of machine learning," where real-world usage data continuously trains algorithms to deliver superior automotive products, ranging from autonomous logistics trucks to seamlessly intuitive, predictive in-cabin experiences.

Capitalizing on this potential requires managing staggering volumes of information, as modern vehicles generate up to ten terabytes of edge data daily. This reality forces a foundational architectural paradigm shift. Traditional waterfall software engineering cannot support the agile, data-centric lifecycle of modern intelligent systems. To succeed, engineering organizations must build dynamic vehicle architectures capable of continuous in-car model updates, massive telemetry ingestion, and complex orchestration across embedded network devices that execute millions of lines of code.

Scaling these AI applications introduces steep engineering and hardware challenges. Expensive sensor payloads like LIDAR and advanced multi-camera arrays aggressively consume vehicle profit margins, requiring creative hardware cost optimization. Moreover, deploying machine learning in safety-critical scenarios demands rigorous model interpretability and robustness. Without strict validation, neural networks often rely on spurious data correlations—such as misidentifying a subject based solely on background artifacts—meaning explainable AI remains an absolute necessity before reaching safe, mass-market roadway deployment.

**Keywords:** automotive software architecture, autonomous driving applications, continuous model deployment, vehicle data pipelines, embedded device orchestration, sensor payload costs, LIDAR sensor integration, algorithmic interpretability, neural network robustness, agile machine learning workflows, in-cabin predictive personalization, safety-critical AI deployment, virtuous cycle of machine learning, mobility demand trends, explainable AI validation

## Chapters

1. **Introduction to machine learning in the automotive industry** (00:17) — Centralized artificial intelligence initiatives drive modern software development within the VW group.
1. **Economic footprint of the global automotive industry** (02:38) — The automotive sector generates massive global economic value while employing millions of people worldwide.
1. **Global car sales and the rising demand for mobility** (05:54) — Stagnating global car sales highlight a transitioning economic focus toward expanding future mobility solutions.
1. **How data growth powers machine learning capabilities** (07:08) — The exponential growth of generated data serves as the underlying engine for viable machine learning products.
1. **The virtuous cycle of machine learning in connected cars** (09:44) — Deploying intelligent products generates continuous user data to iteratively improve automotive algorithms.
1. **Automated driving and the project management triangle** (11:13) — Autonomous vehicles subvert traditional product constraints by simultaneously lowering operational costs and increasing travel quality.
1. **Enhancing user experience with intelligent car cockpits** (13:50) — Voice interaction and algorithmic personalization simplify software management inside modern vehicle interiors.
1. **Tackling data volume and sensor cost limitations** (15:02) — Massive volumes of generated vehicle data compound the ongoing challenge of expensive sensor integration.
1. **Managing the complexity of modern car software architectures** (17:57) — Orchestrating millions of lines of code across numerous embedded devices remains a structural hurdle for vehicles.
1. **Shifting to agile workflows for machine learning development** (19:06) — Transitioning toward data-driven, continuous monitoring paradigms replaces traditional waterfall methodologies for intelligent algorithms.
1. **Ensuring robustness and explainability in machine learning** (21:41) — Inherent biases in training datasets necessitate robust methods for interpreting decisions in safety-critical models.
1. **Summary of machine learning capabilities and engineering opportunities** (25:21) — The massive potential of artificial intelligence creates extensive engineering opportunities within modern automotive organizations.

## Related Moments

- [Introduction to safety-critical machine learning in automotive contexts](https://www.wearedevelopers.com/videos/397-what-non-automotive-machine-learning-projects-can-learn-from-automotive-machine-learning-projects) (from "What non-automotive Machine Learning projects can learn from automotive Machine Learning projects")
- [Navigating automotive complexity with AI runtime environments](https://www.wearedevelopers.com/videos/198-developing-an-ai-sdk) (from "Developing an AI.SDK")
- [Industrial applications of machine learning in autonomous vehicles](https://www.wearedevelopers.com/videos/260-getting-started-with-machine-learning) (from "Getting Started with Machine Learning")
- [Driving developer productivity with AI in automotive tech](https://www.wearedevelopers.com/videos/916-beyond-the-hype-real-world-ai-strategies-panel) (from "Beyond the Hype: Real-World AI Strategies Panel")
- [Defining critical competencies for automotive AI engineering](https://www.wearedevelopers.com/videos/198-developing-an-ai-sdk) (from "Developing an AI.SDK")
- [Addressing participant questions on liability and machine learning](https://www.wearedevelopers.com/videos/374-the-future-of-automotive-mobility-upcoming-e-e-architectures-v2x-and-its-challenges) (from "The future of automotive mobility: Upcoming E/E architectures, V2X and its challenges")

## Related Articles

- [How software is steering vehicle technology](https://www.wearedevelopers.com/magazine/515-how-software-is-steering-vehicle-technology)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)
- [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it)
- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)

## Related Jobs

- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1355348-machine-learning-engineer) at **TWILIO**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/588393-machine-learning-engineer) at **Twilio**
- [Principal Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1706410-principal-machine-learning-engineer) at **Almedia**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1597388-machine-learning-engineer) at **ZEISS Group**
- [Staff Software Engineer, Copilot Experiences](https://www.wearedevelopers.com/jobs/ext/164361-staff-software-engineer-copilot-experiences) at **GitHub**
- [AI Software Engineer (Germany)](https://www.wearedevelopers.com/jobs/48317-ai-software-engineer-germany) at **Sunhat**