Finding the unknown unknowns: intelligent data collection for autonomous driving development

What if you could cut autonomous driving data collection by 99.9%? Learn how an in-car AI identifies and uploads only the most valuable data for retraining.

#1about 1 minute

Finding the unknown unknowns in autonomous driving

The primary challenge in autonomous driving is identifying and collecting data on rare, anomalous scenarios that models are not trained to handle.

#2about 1 minute

Introducing Cariad and its unified software platform

Cariad, a Volkswagen subsidiary, is building a unified software and tech stack to accelerate innovation for all Volkswagen group brands.

#3about 2 minutes

The Big Loop system for intelligent data collection

The Big Loop system solves the high cost of traditional data collection by intelligently aggregating only useful information using dedicated hardware.

#4about 3 minutes

Understanding the long-tail problem in driving scenarios

The long-tail problem refers to rare but critical events, like noisy sensor data or unknown objects, that can be identified using methods like uncertainty estimation.

#5about 3 minutes

How INSTINCT software identifies valuable data

The INSTINCT software uses deep neural networks to analyze sensor data in real-time and calculate an uncertainty score to flag challenging scenarios for collection.

#6about 3 minutes

The complete data-driven development cycle in action

The Big Loop enables a continuous cycle of driving, uploading valuable data, labeling, retraining models, and deploying them back to vehicles via over-the-air updates.

#7about 1 minute

Scaling data collection with the pioneering fleet

The Big Loop technology is being deployed in a retrofitted "pioneering fleet" to scale data collection before its full rollout in millions of future vehicles.

#8about 5 minutes

Q&A on ethics, model deployment, and regional data

The discussion covers ethical dilemmas, local vs cloud model execution, setting dynamic uncertainty thresholds, and the goal of creating globally applicable models.