AI introduces a new dimension of complexity to automotive software, requiring both an AI.SDK for development and an AI Runtime for in-car execution.
The end-to-end machine learning loop involves cloud-based data processing, training, and optimization, followed by in-car deployment, inference, and monitoring.
The AI Runtime Environment abstracts hardware and manages optimized model inference within the centralized Volkswagen Operating System (VW.OS).
Models can be deployed as a standard format like ONNX for on-device compilation or as a pre-compiled binary from the cloud for direct execution.
An AI.SDK provides a standardized and abstracted way to develop applications, tackling the challenges of AI safety and a heterogeneous hardware landscape.
The data preparation component of the SDK standardizes pre-processing, ensures data consistency, and enriches metadata to enable traceability and active learning.
The AI.SDK includes components for performance evaluation and adversarial robustness checks, using a dedicated DNN test metric library for standardization.
The productionization step uses techniques like compression, quantization, and neural architecture search to reduce model size and improve inference time on target hardware.
Working in automotive AI requires a mix of software, hardware, and statistics skills to tackle challenges like massive data volumes and embedded system constraints.
The team uses standard MLOps tools like TensorFlow, PyTorch, and MLflow on the Azure cloud and is actively hiring for open positions.
24:07Mike Butcher, Jürgen Müller, Katrin Lehmann & Tobias Regenfuss
30:49Marin Niehues
48:01Jan Zawadzki
31:23Sayed Bouzouraa
52:10Nico Schmidt
26:55Jan Zawadzki
1:18:27Ulrich Wurstbauer & Mohamed Nassar
41:06Pascal Reddig, TJ Griffiths, Fabian Schmidt, Oliver Winzenried & Matthias Niehoff & Mirko Ross
Jobs that call for the skills explored in this talk.
DTS Systeme GmbH
Airbus Deutschland GmbH
Everllence SE
E Airbus Defence and Space GmbH