Your browser doesn't support javascript. This means that the content or functionality of our website will be limited or unavailable. If you need more information about Vinnova, please contact us.

Unparalleled gridlock forecasting app attributed to unique stochastic AI optimization algorithm

Reference number
Coordinator XIMANTIS AB
Funding from Vinnova SEK 500 000
Project duration August 2018 - February 2019
Status Completed

Purpose and goal

The project aimed to show the benefits of the XIMANTIS Forecaster on congestion hot spots, to proactively manage a journey for a positive environmental impact, improving efficiencies and quality of life. We devised a real-time data collection network, able to issue instant predictive analytics for vehicle navigation systems and traffic control centers (proactive traffic lights). We were also able to greatly expand our capabilities with dynamic parking pricing and develop demand forecasting methods.

Expected results and effects

Our hybrid algorithm was greatly improved by predicting traffic metrics extending over 2 hours in future time with fine granularity / high accuracy. Our MVP demonstrated considerable improvement to traffic flow on traffic light intersections. Our technology tools expanded to parking space demand and dynamic pricing. We attracted international interest for B2B applications. Our know-how expanded. We will have opportunity to file for additional IP.

Planned approach and implementation

We focused on the following objectives: 1)Defined and implemented a MVP 2)Searched/ collaborated with municipality for the MVP 3)Improved Machine Learning capabilities 4)Assembled an AWS secure MVP Back-end for an App or Web 5)Designed and outsourced an App/website Front-end 6)Executed MVP pilot (In Gothenburg) 7)Explored B2B opportunities with parking application (CES 2019, Barcelona, Paris) 8)Explored IP benchmarking, new IP opportunities, functionalities.

External links

The project description has been provided by the project members themselves and the text has not been looked at by our editors.

Last updated 8 January 2019

Reference number 2018-03090

Page statistics