Dynamic lane-level vehicle navigation with lane group identification

Patent metadata

Field	Value
Publication number	US-10895468-B2
Application number	US-201815950035-A
Country	US
Kind code	B2
Filing date	Apr 10, 2018
Priority date	Apr 10, 2018
Publication date	Jan 19, 2021
Grant date	Jan 19, 2021

Abstract

The disclosure includes a system and method for dynamic vehicle navigation with lane group identification. The system includes one or more processors configured to identify a plurality of roadway lanes on a plurality of roads, determine a plurality of lane groups in the plurality of roadway lanes based on traffic data indicating traffic on the plurality of roadway lanes, and estimate lane-group level traffic of the plurality of lane groups based on the traffic on the plurality of roadway lanes. The processors may further identify a client device location of a client device and a destination location, optimize a route between the client device location and the destination location using the plurality of roads and based on the lane-group level traffic of the plurality of lane groups, and provide route guidance to the client device based on the optimized route.

First claim

What is claimed is:

1. A computer-implemented method comprising:
identifying, by a processor, a plurality of roadway lanes on a plurality of roads;
determining a lane-level average speed of each roadway lane of the plurality of roadway lanes;
determining a level of similarity among the lane-level average speed for two or more roadway lanes of the plurality of roadway lanes;
classifying the plurality of roadway lanes into two or more lane groups based on a threshold level of similarity of the lane-level average speed among the plurality of roadway lanes, at least one of the two or more lane groups including at least two roadway lanes, the two or more lane groups in the plurality of roadway lanes including one or more static lane groups and one or more temporary lane groups;
determining the one or more temporary lane groups in the plurality of roadway lanes based on a variation in lane-level average speeds among adjacent lanes of the plurality of roadway lanes, the one or more temporary lane groups including different roadway lanes of the plurality of roadway lanes than the one or more static lane groups;
estimating, by the processor, lane-group level traffic of the two or more lane groups based on traffic on the plurality of roadway lanes;
identifying, by the processor, a client device location of a client device and a destination location;
optimizing, by the processor, a route between the client device location and the destination location using the plurality of roads and based on the lane-group level traffic of the two or more lane groups; and
providing, by the processor, route guidance to the client device based on the optimized route.

2. The computer-implemented method of claim 1 , further comprising determining the one or more static lane groups in the plurality of roadway lanes based on road geometries of the plurality of roadway lanes.

3. The computer-implemented method of claim 1 , wherein estimating the lane-group level traffic of the two or more lane groups includes estimating a current lane-level travel time of the plurality of roadway lanes using a real-time lane-level average speed and a length of a roadway, the lane-group level traffic being based on the current lane-level travel time.

4. The computer-implemented method of claim 3 , wherein estimating the lane-group level traffic of the two or more lane groups includes combining lane-level information in a particular lane group of the two or more lane groups to determine the lane-group level traffic, the lane-level information including the current lane-level travel time and a predicted lane-level travel time.

5. The computer-implemented method of claim 4 , wherein estimating the lane-group level traffic of the two or more lane groups includes:
applying, by the processor, historical lane-level traffic information to a machine learning algorithm to generate a predictive model, and
inputting, by the processor, the current lane-level travel time as an initial state in the predictive model to determine the predicted lane-level travel time.

6. The computer-implemented method of claim 1 , wherein optimizing the route between the client device location and the destination location includes determining the route between the client device location and the destination location by combining at least two of the two or more lane groups to create a path between the client device location and the destination location.

7. The computer-implemented method of claim 6 , wherein the optimized route includes a lane-level routing indicating a use of which lanes reduces total travel time of the route.

8. The computer-implemented method of claim 7 , wherein optimizing the route between the client device location and the destination location includes generating the lane-level routing based on real-time group travel time and a predicted group travel time.

9. A system comprising:
a processor;
a non-transitory storage device; and
a navigation application executable to:
identify a plurality of roadway lanes on a plurality of roads;
determining lane-level average speeds of the plurality of roadway lanes;
determining a level of similarity of the lane-level average speeds among the plurality of roadway lanes;
classifying the plurality of roadway lanes into two or more lane groups based on a threshold level of similarity of the lane-level average speeds among the plurality of roadway lanes, at least one of the two or more lane groups including two or more roadway lanes, the two or more lane groups in the plurality of roadway lanes including one or more static lane groups and one or more temporary lane groups;
determine the one or more temporary lane groups in the plurality of roadway lanes based on a variation in the lane-level average speeds among adjacent lanes of the plurality of roadway lanes, the one or more temporary lane groups including different roadway lanes of the plurality of roadway lanes than the one or more static lane groups;
estimate lane-group level traffic of the two or more lane groups based on traffic on the plurality of roadway lanes;
identify a client device location of a client device and a destination location;
optimize a route between the client device location and the destination location using the plurality of roads and based on the lane-group level traffic of the two or more lane groups; and
provide route guidance to the client device based on the optimized route.

10. The system of claim 9 , wherein the navigation application is further executable to determine the one or more static lane groups in the plurality of roadway lanes based on a lane-level average speed among the adjacent lanes of the plurality of roadway lanes.

11. The system of claim 9 , wherein estimating the lane-group level traffic of the two or more lane groups includes estimating a current lane-level travel time of the plurality of roadway lanes using a real-time lane-level average speed and a length of a roadway, the lane-group level traffic being based on the current lane-level travel time.

12. The system of claim 11 , wherein estimating the lane-group level traffic of the two or more lane groups includes combining lane-level information in a particular lane group of the two or more lane groups to determine the lane-group level traffic, the lane-level information including the current lane-level travel time and a predicted lane-level travel time.

13. The system of claim 12 , wherein estimating the lane-group level traffic of the two or more lane groups includes:
applying historical lane-level traffic information to a machine learning algorithm to generate a predictive model, and
inputting the current lane-level travel time as an initial state in the predictive model to determine the predicted lane-level travel time.

14. The system of claim 9 , wherein optimizing the route between the client device location and the destination location includes determining the route between the client device location and the destination location by combining at least two of the two or more lane groups to create a path between the client device location and the destination location.

15. The system of claim 14 , wherein the optimized route includes a lane-level routing indicating a use of which lanes reduces total travel time of the route.

16. The system of claim 15 , wherein optimizing the route between the client device location and the destination location includes generating the lane-level routing based on real-time group travel time and a predicted group travel time.

Assignees

• Toyota Motor Co Ltd

Inventors

• Yang Hao

Classifications

• G01C21/3415 Primary

  Dynamic re-routing, e.g. recalculating the route when the user deviates from calculated route or after detecting real-time traffic data or accidents · CPC title

• G01C21/3492

  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 title

• G08G1/0137

  for specific applications · CPC title

• G01C21/3658 Primary

  Lane guidance · CPC title

• G08G1/0125

  Traffic data processing · CPC title