Liang Yu

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.

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

Related jobs
Jobs that call for the skills explored in this talk.

Machine Learning Engineer

Picnic Technologies B.V.

Picnic Technologies B.V.
Amsterdam, Netherlands

Intermediate
Senior
Python
Structured Query Language (SQL)
+1

Matching moments

Increasing the value of talk recordings post-event
04:57 MIN

Increasing the value of talk recordings post-event

Cat Herding with Lions and Tigers - Christian Heilmann

Establishing a single source of truth for all data
02:39 MIN

Establishing a single source of truth for all data

Cat Herding with Lions and Tigers - Christian Heilmann

Why corporate AI adoption lags behind the hype
03:28 MIN

Why corporate AI adoption lags behind the hype

What 2025 Taught Us: A Year-End Special with Hung Lee

Automating formal processes risks losing informal human value
03:48 MIN

Automating formal processes risks losing informal human value

What 2025 Taught Us: A Year-End Special with Hung Lee

Moving beyond headcount to solve business problems
04:27 MIN

Moving beyond headcount to solve business problems

What 2025 Taught Us: A Year-End Special with Hung Lee

The future of recruiting beyond talent acquisition
03:15 MIN

The future of recruiting beyond talent acquisition

What 2025 Taught Us: A Year-End Special with Hung Lee

Incentivizing automation with a 'keep what you kill' policy
05:18 MIN

Incentivizing automation with a 'keep what you kill' policy

What 2025 Taught Us: A Year-End Special with Hung Lee

Balancing the trade-off between efficiency and resilience
03:38 MIN

Balancing the trade-off between efficiency and resilience

What 2025 Taught Us: A Year-End Special with Hung Lee

Featured Partners

Related Videos

See all videos
Intelligent Data Selection for Continual Learning of AI Functions52:10

Intelligent Data Selection for Continual Learning of AI Functions

Nico Schmidt

What non-automotive Machine Learning projects can learn from automotive Machine Learning projects48:01

What non-automotive Machine Learning projects can learn from automotive Machine Learning projects

Jan Zawadzki

How Machine Learning is turning the Automotive Industry upside down26:55

How Machine Learning is turning the Automotive Industry upside down

Jan Zawadzki

Uncertainty Estimation of Neural Networks1:00:28

Uncertainty Estimation of Neural Networks

Tillman Radmer & Fabian Hüger & Nico Schmidt

Developing an AI.SDK38:12

Developing an AI.SDK

Daniel Graff & Andreas Wittmann

Automated Driving - Why is it so hard to introduce31:23

Automated Driving - Why is it so hard to introduce

Sayed Bouzouraa

On the straight and narrow path - How to get cars to drive themselves using reinforcement learning and trajectory optimization42:18

On the straight and narrow path - How to get cars to drive themselves using reinforcement learning and trajectory optimization

Francis Powlesland & Elena Kotljarova

How computers learn to see – Applying AI to industry22:11

How computers learn to see – Applying AI to industry

Antonia Hahn

Related Articles

View all articles
DC
Daniel Cranney
How software is steering vehicle technology
The automotive industry is entering a transformative era, and developers have a unique opportunity to be part of it. Cars are no longer just mechanical machines; they’re sophisticated tech platforms with software at their core. This shift, defined by...
How software is steering vehicle technology

From learning to earning

Jobs that call for the skills explored in this talk.