AI Aware

Important results from the project

The AI AWARE project has explored how multiple datasets can be analyzed using AI algorithms to identify roads with an elevated accident risk. Massive real-time data streams as well as large historic datasets have been evaluated by the project and then used to feed the AI algorithm. The ability to turn huge, but currently under-utilized, datasets into specific and quantified accident risk predictions may be used for proactive traffic management that ultimately could prevent accidents to occur. This would be a huge gain in the efforts to create a safer traffic system.

Expected long term effects

The AI AWARE project has successfully met its goals and not only implemented a first version of an AI-powered data fusion platform but also established and tested an end-to-end data flow mechanism to make the accident risk predictions immediately available to many connected organizations. All project members sees great potential in continuing the exploration of predictive awareness for increased traffic safety within their own organizations.

Approach and implementation

OEM, telecom, and location data providers as well as traffic management authorities have been collaborating in the project to provide their knowledge, innovative concepts, and technology. Volvo Cars together with Zenseact created a data fusion platform that applies an AI algorithm for continuous accident risk evaluation on a road segment level. HERE made their “HERE Platform” available for the project, used both as a plentiful data source for Volvo Cars/Zenseact’s AI algorithm as well as a communication layer to forward predicted accident risks to a Central Traffic Control.