What will the vehicles of the future look like? How will drivers and passengers interact with them? How is autonomous driving going to become a reality? These are some of the many questions a group of engineers, designers, scientists and futurists are answering at Volkswagen Group of America’s Innovation Center California (ICC) in Silicon Valley.
At the ICC, one of three global research centers for Volkswagen Group Innovation, the team’s charter is as inspiring as it is challenging: to predict what the world will look like in 2030 and beyond. Forecasting the far future helps the automaker better anticipate and identify the needs of its customers across its worldwide family of brands, including Audi, Bentley, Bugatti, Lamborghini and Volkswagen.
To show the future, the ICC doesn’t use a crystal ball. It uses Unity. With expertise spanning film and animation, software engineering, and VR development and design, the ICC’s group of Unity users stretch the software to its full capabilities to solve diverse problems, including:
- Interaction with far-future scenarios (interior and exterior design and customer journey design)
- Human-machine interface (HMI) design, including 3D user interfaces (UIs)
- Synthetic data generation for machine learning-powered products
The ICC provided a behind-the-scenes look at their work in these areas. Learn more in our report co-created with the ICC.
Here’s a sneak peek at what’s inside the report.
Interaction with far-future scenarios
Visualizing and exploring design concepts in VR
Unity is a key component of the ICC’s visualization pipeline, according to Alisia Martinez and Andrew Gwinner, frontend XR software engineers, and Dij Jayaratna, a senior product designer. “Using Unity, we’ve built projects for tethered and standalone VR headsets, mobile AR devices, custom controllers, in-vehicle experiences, and rendered cinematic videos.”
The audiences for these projects range from product designers assessing the ergonomics of their designs to management reviewing final vehicle concepts. The team brings computer-aided design (CAD) data into Unity using Pixyz and then creates interactive experiences across different platforms to ideate, prototype and communicate.
“The translation of a concept to an interactive experience is rarely perfect on the first pass,” said Martinez, Gwinner and Jayaratna. “Being able to have our designers provide notes in real-time allows us to reach the ideal representation of the concept much more quickly than if we were using other tools.”
How much faster? The team estimates its Unity-based workflow visualizes content in less than half the time and cost as traditional methods.
Realistic 3D UI and HMI design
HMI interaction prototyping in VR
When it comes to in-vehicle experience design, Unity’s tools help the ICC design richer and more immersive content for future vehicle human-machine interfaces (HMI), which go beyond the center console screen and into instrument clusters and head-up displays (HUDs).
“Having a game engine as our base allows us to have much more complex interactions and visualizations,” said Martinez and Loren Skelly, senior manager of UX Design & Concepts. “We can get pretty far designing concepts on our computer screens and test benches, but to truly test our concepts, nothing compares to having an in-car driving experience. Our toolchain with Unity allows us to do that … The ability to test a proof of concept in-vehicle and give feedback directly to our software team to make adjustments to the car in real-time is unparalleled.”
Synthetic data generation
The ICC uses machine learning (ML) and computer vision extensively to develop products that improve over time and with customer usage. One of the key components of these ML-powered products is structured and labelled data. Acquiring this data in the real world can be time-consuming and expensive. At the ICC, synthetic data is emerging as a more affordable, scalable alternative to generating this ML training data.
“Most perception neural networks rely on labeled data, which is costly and prone to error,” said the ICC’s Elnaz Vahedforough, technical project manager. “By using synthetic data, once the labeling task is set up, the labeling is essentially free, and other costs are minimized.”
The ICC generates images and ground-truth data in Unity to train neural networks for implementation of autonomous driving components, such as sensors, perception, prediction and driving.
Besides the cost considerations, synthetic data generated with Unity can be used to construct scenarios that rarely occur (e.g., accidents, unusual objects on the road, etc.) or harsh weather conditions such as fog or heavy rain. Vahedforough noted, “This makes it possible to recreate edge-case scenarios safely.”
As the ICC charts its path forward, the group works hand in hand with Unity’s Integrated Success team. “As experienced Unity users, we know there are a million ways to do one thing, and a million more ways to optimize it,” said Martinez and Skelly. “The Unity Integrated Success team helps us identify the ideal way as we focus on the experience we are trying to create, while achieving the best design and implementation.”
Learn more about the ICC’s innovative work with Unity in this report.
Inspired by VW’s cutting-edge capabilities? Bring the power of these technologies to your business.
- Unity Industrial Collection – Create interactive visualization experiences from CAD and 3D data for mobile devices, PCs, AR and VR devices and other platforms. Try or buy online today.
- Unity Computer Vision – Create high-quality synthetic datasets for computer vision training and validation.
- Unity for HMI – Connect HMI development processes, from design to deployment, to create stunning, interactive user experiences for in-vehicle infotainment (IVI) systems and digital cockpits.