A project team from the Audi Electronics Venture (AEV) is set to exhibit an innovative pre-development project this week at the NIPS conference, which is the world’s most important symposium for artificial intelligence (AI). The Audi project which explores the use of AI in automated driving solutions involves using a mono camera with AI capabilities to generate an extremely precise 3D model of a vehicle’s environment and specific details of its surroundings. The conference, which is co-sponsored by Audi, takes place from 4th – 9th December in Long Beach, California (USA).
A conventional front camera acts as the sensor capturing the area in front of the car within an angle of about 120 degrees. The camera delivers 15 images per second at a resolution of 1.3 megapixels, which are processed in a neural network. Semantic segmenting ensures each pixel is classified into one of 13 object classes, enabling the system to identify and differentiate from other cars, trucks, houses, road markings, people and traffic signs.
The system also uses neural networks for distance information. The visualisation is performed here via ISO lines – virtual boundaries that define a constant distance. This combination of semantic segmenting and estimates of depth produces a precise 3D model of the actual environment.
Independent Learning Capabilities
Audi engineers had previously trained the neural network with the help of “unsupervised learning.” In contrast to supervised learning, unsupervised learning is a method of learning from observations of circumstances and scenarios that do not require pre-sorted and classified data. The neural network received numerous videos of road situations that had been recorded with a stereo camera. As a result, the network learned to independently understand rules, which it uses to produce 3D information from the images of the mono camera. AEV’s project holds great potential for the interpretation of traffic situations.
The Audi team from the Electronics Research Laboratory of Belmont, California, will also be demonstrating a solution for purely AI-based parking and driving in car parks and on motorways. In this process, the lateral guidance of the car is completely carried out through neural networks. The AI learns to independently generate a model of the environment from camera data and to steer the car. This approach does not require a precise localisation or highly precise map data.
The new Audi A8 is the first car in the world developed for conditional automated driving at Level 3 (SAE). The Audi AI traffic jam pilot handles the task of driving in slow-moving traffic up to 60 km/h provided that laws in the market allow it and the driver selects it. Automated driving requires a mapped image of the surrounding environment, as precise as possible, at all times. Artificial intelligence is a key technology for this to become a reality.
In developing autonomous driving cars, Audi is benefiting from a large network in the artificial intelligence field of technology. The network includes companies in the hotspots of Silicon Valley, in Europe and in Israel.