How BMW Group embraced AI for positive use cases and to improve sustainability | AWS re:Invent

Artificial intelligence (AI) helps many different industries and has a particularly strong impact in the automotive industry. One of the most exciting use cases is for fully autonomous vehicles, but that’s not the only area where AI is having an impact. For example, Microsoft and Mercedes-Benz are working together to improve the efficiency of automobile production.

At the AWS re:Invent cloud conference this week, BMW Group described the impact AI has had on its organization and detailed emerging use cases where AI will drive positive future business outcomes.

In a session, Marco Görgmaier, GM, Data Transformation and Artificial Intelligence, BMW Group, said his team has built a library of thousands of data assets across the company that can be reused for analytics. and AI. Since 2019, he said his team has been able to deliver over 800 use cases that have earned over $1 billion in US dollars. Use cases cover research and development, logistics, sales, quality, and supplier network.

“Our team’s vision and mission is to drive and expand business value creation through the use of AI in our value chain,” Görgmaier said.

BMW is heading towards a sustainable future with the help of AI

An emerging area in which BMW is now investing resources is to help improve sustainability.

Görgmaier pointed out that 60% of the world’s population lives in cities and urban areas and that is also where 70% of greenhouse gas emissions are generated. What BMW is now trying to do is help city planners solve problems to help reduce emissions.

BMW is already helping with machine learning models that can predict how road regulations can potentially help reduce both traffic and gasoline emissions. ML models are also used to help identify where the electric vehicle charging infrastructure is not yet sufficient. Görgmaier said a lack of charging infrastructure is preventing people from switching to an electric vehicle, which has an impact on sustainability.

There is also an effort by BMW ML to help predict the impact of parking space availability and pricing on driving habits. These patterns include commuting routes and traffic, which will also impact emissions.

Generating Geospatial Information with Amazon SageMaker

Görgmaier said many of the urban sustainability issues that BMW is trying to help solve can benefit from geospatial information. This is where BMW is starting to use new geospatial capabilities from the Amazon SageMaker ML suite of tools that were just publicly revealed this week.

One of the areas where BMW is looking to leverage geospatial ML is to help predict when an organization with a fleet of vehicles will be able to transition to electric vehicles.

“We set the goal of training machine learning models to learn correlations between engine type and driving profiles,” he said. “The logic behind this was that if such a correlation existed, then the model could learn to predict certain drivers’ affinity for an electric vehicle based on their profiles.”

Because BMW was working with fully anonymized data at the fleet level, it had to use GPS tracks and geospatial data to make the correlations.

“At the end of the training, the model was able to predict the likelihood of specific fleets converting to electric vehicles with over 80% accuracy,” Görgmaier said.