Google files for patent for its ML model speed prediction to improve navigation in India

Tech major Google has moved the Indian patent office seeking a patent to its new machine learning (ML) model for prediction of the speed of vehicles on particular routes, which will provide users the accurate travel time through its app Google Maps.

Google Maps is a web mapping service developed by Google. It offers satellite imagery, aerial photography, street maps, 360° panoramic views of streets, real-time traffic conditions, and route planning for traveling by foot, car, bicycle and air (in beta), or public transportation.

At present, the available navigation services predict a faster or best route and recommend that route to a user via a geographical user interface.

Google intends to predict the travel time depending on the speed of the vehicle and recommend suitable routes to the user. According to the patent document filed by Google, a novel computer system is incorporated in the machine learning model specifically adapted to perform a task related to the real world: predicting the speed of a vehicle of a particular type on a specific road segment.

According to Google, such accurate speed predictions could be used to provide better route selection for the enhanced travel mode. When a navigation request is made in connection with the enhanced travel mode, for instance, a map depicting a best route may be presented along with certain points of interests that are likely to be useful as landmarks, but would not otherwise be displayed to the user at the current zoom level.

Google submitted that the method includes receiving first tracking data indicative of individual speeds of first vehicles while travelling on road segment at various times, and second tracking data indicative of individual speeds of second vehicles while travelling on the same road segment at the same time.