Miniscule prototype created to showcase Audi’s first step towards artificial intelligence

Concept vehicles come in a variety of shapes and sizes. That’s just part of the game the auto industry has been playing to showcase new technologies or styling languages for its future production lineup. For its part, Audi has developed concept vehicles of its own, but none of those concepts are as different as the Audi Q2 “Deep Learning Concept,” a prototype that’s as unique for the technology it’s previewing as much as for it’s actual size.

See, the Q2 Deep Learning Concept isn’t a traditional car. Far from it, actually. It’s a 1:8 scale model that Audi built as a demonstrator to showcase the new deep learning technology. Without sounding too technical about the concept or deep learning technology, the whole thing is essentially Audi’s way of introducing the space of artificial intelligence into the auto industry. In the case of the Q2 Deep Learning Concept, that involves showcasing a system that allows vehicles to find parking spots entirely on their own.

One look at the Q2 concept tells you as much, particularly the presence of ultrasonic sensors scattered throughout the front and sides of the car. These sensors are responsible for scanning and retrieving data around the vehicle and work in concert with an on-board computer that, in turn, process the data and converts them into control signals for the car’s steering and powertrain. Once the data is processed, the car makes the appropriate responses and drives itself around a parking lot until it can find a spot to park, doing all of this by itself without any assistance from a human driver.

The whole system is underpinned by another technological development that Audi’s cooking up called “deep reinforcement learning.” In so many words, the process basically means that a specific car learns “knowledge” similar to us humans. In its case, it could revolve around trying to find easy parking spots before learning more sophisticated parking maneuvers over time.

All of these systems and advancements are being presented by Audi and the 1:8 scale Q2 Deep Learning Concept at the Conference and Workshop on Neural Information Processing Systems, an event that showcases the latest breakthroughs and developments related to the field of, you guessed it, artificial intelligence. The conference is being held in Barcelona, Spain and is ongoing until December 10, 2016.

Continue after the jump to read the full story.

There’s a place for AI in the future of the auto industry

This is a small preview of what the future of the auto industry is going to look like. Ever remember a time when automakers participated in science-centric conferences? Well, prepare yourselves to see more of this, now that electrification and autonomous mobility have been identified as the future of the business.

Audi’s participation at an event focusing on artificial intelligence isn’t an accident, nor is it going to be a one-time thing. This is where the business is headed and as research and development advances to the point of actual application, you’re going to see more companies like Audi showcasing their products to events like this.

It sounds complicated on the surface, maybe even a little out of place. But it’s also a beautiful thing because these car brands are now recognizing the importance of being in sync with the development curve of these scientific segments.

It sounds complicated on the surface, maybe even a little out of place. But it’s also a beautiful thing because these car brands are now recognizing the importance of being in sync with the development curve of these scientific segments. If they get left behind, it’s going to be a lot more difficult to adapt to the changes in these fields, especially if these changes happen in as rapid a pace as autonomous driving technology.

For those who don’t know, this is Audi’s first time attending the Conference and Workshop on Neural Information Processing Systems. It also likely won’t be the last now that the German automaker has dipped its toes into this scientific ecosystem.

The adaptation of artificial intelligence into the auto industry might still be cloudy at this point in time, but as the Q2 Deep Learning Concept is currently showing us, that picture could become clearer once the technology developed by automakers in this field speeds up.

Kirby Garlitos
Automotive Aftermarket Expert -
Kirby’s first exposure into the world of automobiles happened when he caught Knight Rider on television as a five-year old boy. David Hasselhoff didn’t leave much of an impression on him (that happened later on in Baywatch), but KITT certainly did. To this day, Kirby remains convinced that he will one day own a car with the same ‘spirit’ as the original KITT (not the 2008 monstrosity). He doesn't know when that will be, but until then, he’s committed to expressing his love for KITT, and all cars for that matter, here at TopSpeed.  Read More
About the author

Press Release

It’s one of the world’s most important specialist conferences for artificial intelligence: Every year the Conference and Workshop on Neural Information Processing Systems (NIPS) presents advances in the fields of machine learning and computational neuroscience. Audi is showcasing its expertise at the conference for the first time. From December 5 to 10, 2016, in Barcelona, the premium automaker is showing with the aid of a scale model how a car develops intelligent parking strategies. The car manufacturer is also providing specialists and potential applicants with information on jobs in innovative fields.

Self-learning systems are a key technology for piloted driving cars. That’s why Audi has already built up a wealth of know-how in machine learning. The company is the only automaker represented at NIPS with its own stand and a showcase. A 1:8 scale model car – the “Audi Q2 deep learning concept” – is demonstrating an intelligent parking process. On an area measuring 3 x 3 meters, it autonomously searches for and finds a suitable parking space in the form of a metal frame, and then parks itself there.

The Audi Q2 Deep Learning Concept is the coolest 1:8 Scale Model You've Ever Seen High Resolution Exterior
- image 697419

The Audi Q2 deep learning concept’s sensor technology consists of two mono cameras, facing forward and toward the rear, along with ten ultrasonic sensors positioned at points all around the model. A central on-board computer converts their data into control signals for steering and the electric motor. On the driving surface, the model car first determines its position relative to the parking space. As soon as it perceives the position, it calculates how it can safely drive to its targeted destination. The model car maneuvers, steers and drives forward or in reverse, depending on the situation.

The model car’s parking ability is made possible by deep reinforcement learning. In other words, the system essentially learns through trial and error. To begin, the car selects its direction of travel at random. An algorithm autonomously identifies the successful actions, thus continually refining the parking strategy. So in the end the system is able to solve even difficult problems autonomously.

The Audi Q2 Deep Learning Concept is the coolest 1:8 Scale Model You've Ever Seen High Resolution Exterior
- image 697422

The Audi Q2 deep learning concept is a pre-development project of Audi Electronics Venture (AEV), an AUDI AG subsidiary in Gaimersheim, Germany. In the next step, the developers are transferring the parking-space search process to a real car.

The Audi global network encompasses not only research institutes, but also companies from hotspots in California’s Silicon Valley, Europe and Israel. The premium manufacturer is working with partners including Mobileye, the world’s leading company in the field of image recognition. In this partnership, the two companies combined their expertise to develop a deep learning-based software for environment perception systems. Audi will use the software for the first time in 2017, in the central driver assistance controller (zFAS) in the new generation of the Audi A8. NVIDIA, a leader in the field of hardware systems with an associated development environment, was an important partner in the development of the zFAS. These technical solutions will enable the customer to enjoy piloted driving in traffic jam situations as well as piloted parking.

The Audi Q2 Deep Learning Concept is the coolest 1:8 Scale Model You've Ever Seen High Resolution Exterior
- image 697421

Audi is further intensifying its collaborations with partners from high-tech industries through an increasing degree of integration of components with artificial intelligence (AI). These forms of artificial intelligence are important for dealing with challenging situations such as urban traffic. It enables piloted driving cars to evaluate their complex surroundings and perform necessary driving maneuvers accordingly.

Also at NIPS to gain insights into these and other exciting developments will be AI specialists interested in working on innovations at Audi. Specialists and HR experts from the company will be at the event to provide them with information on a range of career opportunities. At Audi the specialists will have opportunities to help shape the role of AI in the automotive industry by applying their knowledge in the areas of machine learning, cloud computing, data analytics and vehicle architecture.

View the full press release Hide press release
Press release
What do you think?
Show Comments
Car Finder: