Press "Enter" to skip to content

Google seeks patent for ML model speed prediction to improve navigation services

The company said these more accurate speed predictions could be used to provide better route selection for the enhanced travel mode.

In a bid to further strengthen its navigation services, American 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.

Google Maps, a web mapping service offers satellite imagery, aerial photography, street maps, views of streets, real-time traffic conditions, and route planning for travelling by foot, car, bicycle, or public transportation.

Currently, the available navigation services are capable of predicting a faster or best route and recommending that route to a user via a geographical user interface. Determination of a fastest route typically involves an estimate of travel time along various potential routes. However, currently, such estimates are only able to convey differences in very different travel modes along different travel channels such as driving, walking, cycling and public tansit.

According to 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. The prediction of the speed of the vehicle can be used to predict a travel time, or recommend a route to the user.

In the former case, this allows a user to undertake a journey only if the predicted time is acceptable, while in the latter case, it permits the journey to be undertaken with a route having a lower predicted travel time. In both cases, the prediction results in the technical effects of reducing the wasteful travel time and reducing the consumption of resources associated with the travel, including the fuel.

The company said these more 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 example, a map depicting a best route may be presented along with certain points of interets 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.

Get live Stock Prices from BSE and NSE and latest NAV, portfolio of Mutual Funds, calculate your tax by Income Tax Calculator, know market’s Top Gainers, Top Losers & Best Equity Funds. Like us on Facebook and follow us on Twitter.

Source: Financial Express