Home World News Self-Learning Audi Autonomously Masters Complex Parking

Self-Learning Audi Autonomously Masters Complex Parking


Audi has demonstrated its expertise in areas of artificial intelligence (AI) and autonomous driving at the Conference and Workshop on Neural Information Processing Systems (NIPS) in Barcelona, as a concept model Audi Q2 autonomously completed complex parking manoeuvres.

Audi Q2 deep learning concept , model car on a scale of 1:8
Audi Q2 deep learning concept , model car on a scale of 1:8

Self-learning systems are a key technology for autonomous, or ‘piloted’, cars. The 1:8 scale model car, the “Audi Q2 deep learning concept”, autonomously searches for and finds suitable parking spaces in the form of a metal frame on a 3×3-metres area and parks itself there. 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 manoeuvres, steers and drives forwards 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; in the end, the system is able to solve even difficult problems autonomously.

Audi Q2 deep learning concept , model car on a scale of 1:8

The Audi Q2 deep learning concept is a pre-development project of Audi Electronics Venture (AEV) in Germany. In the next step, the developers are transferring the parking-space search process to a real car. Audi is also working with partners including Mobileye, the world’s leading company in 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 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. Audi is intensifying its collaborations with partners in high-tech industries by integrating more AI components into its vehicles. AI is essential for dealing with challenging situations such as urban traffic, enabling piloted driving cars to evaluate their complex surroundings and perform the necessary driving manoeuvres.