Adaptive and personalized navigation system

• US 8,682,574 B2
• Filed: 03/30/2009
• Issued: 03/25/2014
• Est. Priority Date: 11/02/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Golding, Andrew R., Rasmussen, Jens Eilstrup
• Primary Examiner(s): Amin, Bhavesh V
• Application Number:
  US12/414,461
• Publication Number:
  US 20090192705A1
• Time in Patent Office: 1,821 Days
• Field of Search: None
• US Class Current: 701/411
• CPC Class Codes: G01C 21/3484 Personalized, e.g. from learned user behaviour or user-defined profiles
• CPC Class Codes: G01C 21/3492 employing speed data or traffic data, e.g. real-time or historical traffic control systems for road vehicles involving transmission of navigation instructions to the vehicle G08G1/0968
• CPC Class Codes: G01C 21/36 Input/output arrangements for on-board computers

Abstract

Adaptive navigation techniques are disclosed that allow navigation systems to learn from a user'"'"'s personal driving history. As a user drives, models are developed and maintained to learn or otherwise capture the driver'"'"'s personal driving habits and preferences. Example models include road speed, hazard, favored route, and disfavored route models. Other attributes can be used as well, whether based on the user'"'"'s personal driving data or driving data aggregated from a number of users. The models can be learned under explicit conditions (e.g., time of day/week, driver ID) and/or under implicit conditions (e.g., weather, drivers urgency, as inferred from sensor data). Thus, models for a plurality of attributes can be learned, as well as one or more models for each attribute under a plurality of conditions. Attributes can be weighted according to user preference. The attribute weights and/or models can be used in selecting a best route for user.

Claims

1. A machine-readable, non-transitory storage medium encoded with instructions that, when executed by one or more processors, cause the one or more processors to carry out a process for generating directions for use in navigation during a current driving session, the process comprising:

receiving a target destination;

generating at least one candidate route;

probabilistically determining that one of a plurality of conditional variant models associated with a target attribute corresponds to a condition of the target attribute, the plurality of conditional variant models learned from previous user driving sessions;

scoring the at least one candidate route using the determined conditional variant model;

providing a scored route to a user;

detecting a change in the condition of the target attribute,

wherein the detecting a change in the condition of the target attribute comprises;

recomputing probabilities for the conditional variant models associated with the target attribute periodically during the current driving session using subsequently observed data of the current driving session; and

probabilistically determining that a second conditional variant model currently corresponds to the condition of the target attribute; and

providing an altered route to the user based on the detected change.

2. The machine-readable, non-transitory storage medium of claim 1, the process further comprising:

determining a driver ID for the current driving session; and

restricting the plurality of conditional variant models associated with the target attribute to include only conditional variant models associated with the driver ID.

3. The machine-readable, non-transitory storage medium of claim 2, wherein the determining a driver ID for the current driving session comprises at least one selected from a group consisting of:

receiving login criteria associated with the driver ID;

detecting an ignition key associated with the driver ID;

detecting a preferred seat setting associated with the driver ID;

detecting a preferred mirror setting associated with the driver ID; and

detecting a driver weight associated with the driver ID.

4. The machine-readable, non-transitory storage medium of claim 1, wherein the target attribute is a road familiarity attribute.

5. The machine-readable, non-transitory storage medium of claim 4, the process further comprising providing summarized directions for the scored route in response to the road familiarity attribute indicating user familiarity with the scored route.

6. The machine-readable, non-transitory storage medium of claim 5, the process further comprising providing expanded directions for the scored route in response to a user request for additional details of the summarized directions.

7. The machine-readable, non-transitory storage medium of claim 4, the process further comprising providing a visual indicator of a route familiarity level to the user.

8. A computer-implemented method to be implemented via one or more processors, for generating directions for use in navigation during a current driving session, comprising:

receiving a target destination;

generating, via the one or more processors, at least one candidate route;

probabilistically determining, via the one or more processors, that one of a plurality of conditional variant models associated with a target attribute corresponds to a condition of the target attribute, the plurality of conditional variant models learned from previous user driving sessions;

scoring, via the one or more processors, the at least one candidate route using the determined conditional variant model;

providing a scored route to a user;

detecting, via the one or more processors, a change in the condition of the target attribute, wherein detecting a change in the condition of the target attribute comprises;

recomputing probabilities for the conditional variant models associated with the target attribute periodically during the current driving session using subsequently observed data of the current driving session; and

probabilistically determining that a second conditional variant model currently corresponds to the condition of the target attribute; and

providing an altered route to the user based on the detected change.

9. The computer-implemented method of claim 8, the method further comprising:

determining, via the one or more processors, a driver ID for the current driving session; and

restricting, via the one or more processors, the plurality of conditional variant models associated with the target attribute to include only conditional variant models associated with the driver ID.

10. The computer-implemented method of claim 9, wherein the determining a driver ID for the current driving session comprises at least one selected from a group consisting of:

receiving login criteria associated with the driver ID;

detecting an ignition key associated with the driver ID;

detecting a preferred seat setting associated with the driver ID;

detecting a preferred mirror setting associated with the driver ID; and

detecting a driver weight associated with the driver ID.

11. The computer-implemented method of claim 8, wherein the target attribute is a road familiarity attribute.

12. The computer-implemented method of claim 11, the method further comprising providing summarized directions for the scored route in response to the road familiarity attribute indicating user familiarity with the scored route.

13. The computer-implemented method of claim 12, the method further comprising providing expanded directions for the scored route in response to a user request for additional details of the summarized directions.

14. The computer-implemented method of claim 11, the method further comprising providing a visual indicator of a route familiarity level to the user.