Passenger preference route and alternative destination estimator

Patent metadata

Field	Value
Publication number	US-11959760-B2
Application number	US-202217676267-A
Country	US
Kind code	B2
Filing date	Feb 21, 2022
Priority date	Feb 21, 2022
Publication date	Apr 16, 2024
Grant date	Apr 16, 2024

Abstract

Disclosed is a method including obtaining, using at least one processor, a user destination; obtaining, using the at least one processor, preference data indicative of a user route preference; determining, using the at least one processor, based on the user destination and the preference data, a set of routes towards a set of destinations, wherein at least one route of the set of routes is associated with one or more operational metrics; ranking, using the at least one processor, based on the preference data, the routes of the set of routes; and controlling, using the at least one processor, based on at least one of the ranked routes, navigation of an autonomous vehicle Systems and computer program products are also provided.

First claim

What is claimed is:

1. A method comprising:
obtaining, using at least one processor, a user destination for an autonomous vehicle;
obtaining, using the at least one processor, preference data indicative of a user route preference;
performing in parallel, using the at least one processor:
a first search for a first route through a road network to the user destination using a first operational metric and a first optimization goal for the first operational metric, and
a second search for a second route through the road network to the user destination using a second operational metric and a second optimization goal for the second operational metric, wherein the second operational metric is different from the first operational metric and the second optimization goal is different from the first optimization goal;

ranking, using the at least one processor, based on the preference data, the first route and the second route in a first ranking and a second ranking, wherein the first ranking uses a first set of the preference data to rank the first route and the second route and the second ranking uses a second set of the preference data to rank the first route and the second route, wherein the first set of the preference data is different from the first optimization goal and the second set of the preference data is different from the second optimization goal;
selecting the first route or the second route as a driving route based on the first ranking and the second ranking; and
controlling, using the at least one processor, navigation of the autonomous vehicle based on the selected driving route, wherein controlling navigation comprises controlling at least one of steering, breaking, or acceleration of the autonomous vehicle.

2. The method of claim 1 , wherein the preference data comprises one or more attributes indicative of the user route preference.

3. The method of claim 2 , wherein obtaining, using the at least one processor, the preference data comprises assigning, based on a model, a weight to at least one of the first operational metric or the second operational metric.

4. The method of claim 3 , wherein the model is configured to determine, based on previous routes, the assignment of the weight to the at least one of the first operational metric or the second operational metric.

5. The method of claim 3 , wherein the model is a user-specific model.

6. The method of claim 3 , wherein ranking the first route and the second route in the first ranking and the second ranking comprises ranking, using the at least one processor, based on the weight, the first route and the second route.

7. The method of claim 3 , further comprising:
determining, using the at least one processor, an alternative destination based on the user destination and the preference data;
determining using the at least one processor, based on the user destination, the preference data, and the alternative destination, at least one alternative route, and
determining, using the at least one processor, based on the weight, a corresponding operational metric across the at least one alternative route.

8. The method of claim 7 , wherein determining the at least one alternative route comprises minimizing, using the at least one processor, across the at least one alternative route, a cost function of weighted values of the corresponding operational metric.

9. The method of claim 7 , wherein determining the at least one alternative route comprises performing, using the at least one processor, a plurality of searches, in parallel, through a road network towards the alternative destination, wherein the plurality of searches comprises a third search based on a third operational metric and a fourth search based on a fourth operational metric different from the third operational metric.

10. The method of claim 9 , wherein a target parameter of the fourth operational metric diverges from a target parameter of the third operational metric.

11. The method of claim 1 , wherein the first optimization goal comprises a minimization of a cost function of weighted values of the first operational metric.

12. The method of claim 1 , further comprising:
determining, using the at least one processor, an alternative destination based on the user destination and the preference data,
wherein determining the alternative destination comprises:
obtaining, using the at least one processor, feature data, wherein the feature data comprises one or more of: time data, user data, location data, and user selection data; and
determining, using the at least one processor, based on the user destination, the preference data, and the feature data, the alternative destination.

13. The method of claim 1 , further comprising:
determining, using the at least one processor, an alternative destination based on the user destination and the preference data,
wherein determining the alternative destination comprises determining, using the at least one processor, based on the user destination, the preference data, and a neural network model, the alternative destination, wherein the neural network model is configured to estimate the alternative destination.

14. The method of claim 1 , wherein the first set of the preference data used in the first ranking of the first route and the second route comprises common preference data wherein the common preference data is indicative of common preference types.

15. The method of claim 1 , wherein the second set of the preference data used in the second ranking of the first route and the second route comprises preference data indicative of all preferences.

16. The method of claim 1 , further comprising selecting, using the at least one processor, based on the preference data, a highest ranked route from the first ranking and the second ranking.

17. The method of claim 1 , wherein the second optimization goal diverges from the first optimization goal.

18. The method of claim 1 , further comprising:
causing, by the at least one processor, the first route and the second route to be displayed on a display; and
receiving, using the at least one processor, user input indicative of a selection of at least one of the first route or the second route;
wherein controlling, using the at least one processor, the navigation of the autonomous vehicle comprises controlling, using the at least one processor, based on the user input, the navigation of the autonomous vehicle.

19. The method of claim 1 , wherein the preference data comprises learned route preferences of a user based on previously traveled routes.

20. A system comprising:
at least one processor; and
at least one non-transitory computer readable medium storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
obtaining, a user destination for an autonomous vehicle;
obtaining, preference data indicative of a user route preference;
performing in parallel, using the at least one processor:
a first search for a first route through a road network to the user destination using a first operational metric and a first optimization goal for the first operational metric, and
a second search for a second route through the road network to the user destination using a second operational metric and a second optimization goal for the second operational metric, wherein the second operational metric is different from the first operational metric and the second optimization goal is different from the first optimization goal;

rankin

Assignees

• Motional Ad Llc

Inventors

• Cserna Bence
• Gall Kevin C
• Brown Alexander

Classifications

• G05D2101/10

  using artificial intelligence [AI] techniques · CPC title

• B60W2050/0028

  Mathematical models, e.g. for simulation · 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

• B60W60/00253

  Taxi operations · CPC title

• G01C21/3461

  Preferred or disfavoured areas, e.g. dangerous zones, toll or emission zones, intersections, manoeuvre types or segments such as motorways, toll roads or ferries · CPC title