BMW Shares Some of its AI Algorithms Used in Vehicle Production on GitHub

author: Eric Walz   

BMW’s assembly plant in Dingolfing, Germany began series production of the new BMW 8 Series in 2018.

Manufacturing in the auto industry has become high-tech, with automation replacing menial tasks and robots working alongside humans on the vehicle assembly line. 

German automaker BMW operates some of the world's most advanced vehicle production and logistics facilities and the company announced its sharing some of its AI-powered algorithms with the developer community.

BMW announced its making a select group of algorithms available on the popular code-hosting platform Github free for anyone to use. 

These algorithms are available now at github.com/BMW-InnovationLab. 

The algorithms are part of various AI applications used by BMW, and focus primarily on automated image recognition and image tagging. Making these algorithms publicly available allows software developers anywhere in the world to view, change, use and improve upon them.

"With the algorithms we are now publishing, the BMW Group has significantly reduced the development time for neural networks for autonomous transport systems and robots," says Dirk Dreher, Head of Logistics Planning. 

Image recognition is one of the most common tasks in the field of computer vision and much of it relies on deep-learning. Image recognition is the ability to identify objects in images. It uses machine vision technologies with artificial intelligence and trained algorithms to recognize images via a camera system.

When machine learning and image classification are combined, computers become capable of performing visual tasks that once could only be done by humans, making vehicle production more efficient for BMW. The automaker is currently using a number of these artificial intelligence (AI) applications trained algorithms to recognize images through a camera system during production. 

For example, BMW said that AI relieves workers of monotonous tasks such as checking whether the warning triangle is placed exactly in the right spot in the vehicle's trunk on the assembly line. 

Neural networks are used to compare live images in production with image databases to detect any deviations from the target. This once monotonous task is now performed by a camera and self-learning software that compares the camera's live images with hundreds of stored images in just milliseconds. 

"We are making major investments in artificial intelligence. By sharing our algorithms with the global developer community, we want to do our part and make AI accessible to a broad group of users. We expect the further open source development to lead to a rapid and agile advancement of the software," adds Kai Demtröder, Head of Artificial Intelligence, Data Platforms at BMW Group IT.

In keeping with the open source approach, all users of BMW's algorithms on Github are guaranteed anonymity. In addition, any flaws in the algorithms can be identified quickly. 

For quality assurance purposes, the BMW Group checks all incoming user suggestions before they are put into productive use or shared.

Eric Walz

Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.