Situation-aware route and destination predictions

Patent metadata

Field	Value
Publication number	US-10145702-B2
Application number	US-201615262237-A
Country	US
Kind code	B2
Filing date	Sep 12, 2016
Priority date	Jun 9, 2014
Publication date	Dec 4, 2018
Grant date	Dec 4, 2018

Abstract

A method for predicting a destination of a vehicle includes receiving vehicle data from a plurality of sensors, the vehicle data including at least a current location and a current time, determining a plurality of usage scenarios based on the vehicle data, accessing historical vehicle data and user data from a database, assigning, based on the vehicle data, a likelihood value to each of the plurality of usage scenarios, and predicting a set of destinations and routes for each of the plurality of usage scenarios.

First claim

What is claimed is:

1. A method for predicting a destination of a vehicle, the method comprising:
detecting, using a plurality of sensors, vehicle data, the vehicle data including at least a current location and a current time;
providing the vehicle data from the plurality of sensors to a situation detection unit;
determining a plurality of usage scenarios based on the vehicle data;
accessing historical vehicle data and user data from a database;
assigning, based on the vehicle data, a likelihood value to the plurality of usage scenarios;
predicting a set of destinations and routes for the plurality of usage scenarios;
predicting a most likely usage scenario from the plurality of usage scenarios;
displaying the predicted most likely usage scenario to a user on a user interface display and receiving user input such that a user is able to confirm the predicted most likely usage scenario;
storing vehicle data for prior vehicle trips and a reliability score for prior predictions in the database; and
updating the reliability value in the historical database when the user confirms the predicted mostly likely useage scenario,
wherein when the user confirms the predicted most likely usage scenario the system applies settings, corresponding to the predicted mostly likely usage scenario, to in-vehicle systems.

2. The method according to claim 1 , further comprising assigning a weight to the usage scenarios and set of destinations and routes based on the likelihood value and the historical data.

3. The method according to claim 2 , further comprising sorting the usage scenarios and set of destinations and routes based on the weight to obtain a mostly likely set for predictions.

4. The method according to claim 3 , presenting the most likely set of predictions to a user.

5. The method according to claim 1 , wherein the plurality of sensors is configured to detect a variety of vehicle data.

6. The method according to claim 1 , wherein the in-vehicle systems comprise a vehicle navigation system and other in-vehicle systems.

7. The method according to claim 1 , wherein the plurality of sensors is configured to detect external vehicle data and passenger usage parameters.

8. The method according to claim 1 , further comprising applying a weight to each destination in the set of destinations based on a likelihood that the destination matches a particular usage scenario.

9. The method according to claim 8 , wherein the weight is determined based on data stored in the database.

10. A method for predicting a destination of a vehicle, the method comprising:
detecting vehicle data using a sensor;
receiving the vehicle data from the sensor;
determining a plurality of common usage scenarios based on the vehicle data;
determining and assigning a likelihood value for the plurality of common usage scenarios;
transmitting the vehicle data from the sensor and the plurality of common usage scenarios and the likelihood value from the situation detection unit to a navigation system control unit, the navigation system control unit predicting a most likely usage scenario from the plurality of common usage scenarios and determining a set of destinations for the predicted most likely usage scenario;
displaying the predicted most likely usage scenario to a user;
receiving user input such that the user is able to confirm the predicted most likely usage scenario;
storing vehicle data for prior vehicle trips and a reliability value for prior predictions in a historical database;
updating the reliability value in the historical database when the user confirms the predicted most likely usage scenario; and
when the user confirms the predicted most likely usage scenario, applying settings, corresponding to the predicted most likely usage scenario, to in-vehicle systems.

Assignees

• Volkswagen Ag
• Audi Ag

Inventors

• Gerlach Simon

Classifications

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G01C21/3617 Primary

  using user history, behaviour, conditions or preferences, e.g. predicted or inferred from previous use or current movement · CPC title

• G08G1/096838

  where the user preferences are taken into account or the user selects one route out of a plurality · CPC title

• G06N7/005

  Physics · mapped topic

• G08G1/096894

  where input is assisted by the navigation device, i.e. the user does not type the complete name of the destination, e.g. using zip codes, telephone numbers, progressively selecting from initial letters · CPC title