Granted Patent B2

US 12,523,493 · App. 18/078,303 · Granted Jan 13, 2026

Inventor: Alexander Christoph Schaefer (Fremont, CA)

Assignee: Woven By Toyota, Inc.

G01C21/3815G01C21/3811G01C21/3848

Abstract

Claims (82)

1 . A system comprising:

a processor; and

a memory storing machine-readable instructions that, when executed by the processor, cause the processor to:

receive sensor data related to a road portion, the sensor data including a plurality of trace points and a plurality of key points associated with the plurality of trace points, the plurality of trace points being related to positions of a vehicle in the road portion, the plurality of key points being related to lane boundaries;

determine a first probability that two of the trace points are in a same lane, a second probability that the two of the trace points are in adjacent lanes, and a third probability that the two of the trace points are not in the same lane and not in adjacent lanes based on fitting a first curve to the plurality of left key points and fitting a second curve to the plurality of right key points;

determine a relationship between the plurality of trace points based on the first probability, the second probability, and the third probability;

determine characteristics of the road portion based on the relationship, the characteristics including at least a width of one or more lanes in the road portion;

generate a semantic map of the road portion based on the characteristics; and

control operation of a vehicle based on the semantic map.

2 . The system of claim 1 , wherein the characteristics of the road portion include at least one of:

a number of lanes in the road portion;

a position of one or more lane markings on the road portion;

a position of an intersection between two or more lanes; or

a position of one or more boundaries of the road portion.

3 . The system of claim 1 , wherein the relationship is one of:

trace points in a same lane;

trace points in adjacent lanes; or

trace points in non-adjacent lanes.

4 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:

determine the relationship between the plurality of trace points that are within a predetermined proximity to each other.

5 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:

assign a first value indicating a likelihood that the relationship is trace points in a same lane based on the plurality of key points;

assign a second value indicating a likelihood that the relationship is trace points in adjacent lanes based on the plurality of key points;

assign a third value indicating a likelihood that the relationship is trace points in non-adjacent lanes based on the plurality of key points; and

determine the relationship based on the highest of the first value, the second value, and the third value.

6 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:

determine a trajectory for a lane based on the relationship; and

determine the characteristics of the road portion based on the trajectory.

7 . The system of claim 1 , wherein the plurality of key points includes one or more key points, wherein one of the one or more key points is associated with a left lane boundary and an other of the one or more key points is associated with a right lane boundary.

8 . A method comprising:

receiving sensor data related to a road portion, the sensor data including a plurality of trace points and a plurality of key points associated with the plurality of trace points, the plurality of trace points being related to positions of a vehicle in the road portion, the plurality of key points being related to lane boundaries;

determining a first probability that two of the trace points are in a same lane, a second probability that the two of the trace points are in adjacent lanes, and a third probability that the two of the trace points are not in the same lane and not in adjacent lanes based on fitting a first curve to the plurality of left key points and fitting a second curve to the plurality of right key points;

determining a relationship between the plurality of trace points based on the first probability, the second probability, and the third probability;

determining characteristics of the road portion based on the relationship, the characteristics including at least a width of one or more lanes in the road portion;

generating a semantic map of the road portion based on the characteristics; and

controlling operation of a vehicle based on the semantic map.

9 . The method of claim 8 , wherein the characteristics of the road portion include at least one of:

a number of lanes in the road portion;

a position of one or more lane markings on the road portion;

a position of an intersection between two or more lanes; or

a position of one or more boundaries of the road portion.

10 . The method of claim 8 , wherein the relationship is one of:

trace points in a same lane;

trace points in adjacent lanes; or

trace points in non-adjacent lanes.

11 . The method of claim 8 , further comprising:

determining the relationship between the plurality of trace points that are within a predetermined proximity to each other.

12 . The method of claim 8 , further comprising:

assigning a first value indicating a likelihood that the relationship is trace points in a same lane based on the plurality of key points;

assigning a second value indicating a likelihood that the relationship is trace points in adjacent lanes based on the plurality of key points;

assigning a third value indicating a likelihood that the relationship is trace points in non-adjacent lanes based on the plurality of key points; and

determining the relationship based on the highest of the first value, the second value, and the third value.

13 . The method of claim 8 , further comprising:

determining a trajectory for a lane based on the relationship; and

determining the characteristics of the road portion based on the trajectory.

14 . The method of claim 8 , wherein the plurality of key points includes one or more key points, wherein one of the one or more key points is associated with a left lane boundary and an other of the one or more key points is associated with a right lane boundary.

15 . A non-transitory computer-readable medium including instructions that when executed by a processor cause the processor to:

receive sensor data related to a road portion, the sensor data including a plurality of trace points and a plurality of key points associated with the plurality of trace points, the plurality of trace points being related to positions of a vehicle in the road portion, the plurality of key points being related to lane boundaries;

determine a first probability that two of the trace points are in a same lane, a second probability that the two of the trace points are in adjacent lanes, and a third probability that the two of the trace points are not in the same lane and not in adjacent lanes based on fitting a first curve to the plurality of left key points and fitting a second curve to the plurality of right key points;

determine a relationship between the plurality of trace points based on the first probability, the second probability, and the third probability that the two of the trace points are not in the same lane and not in adjacent lanes;

determine characteristics of the road portion based on the relationship, the characteristics including at least a width of one or more lanes in the road portion;

generate a semantic map of the road portion based on the characteristics; and

control operation of a vehicle based on the semantic map.

16 . The non-transitory computer-readable medium of claim 15 , wherein the characteristics of the road portion include at least one of:

a number of lanes in the road portion;

a position of one or more lane markings on the road portion;

a position of an intersection between two or more lanes; or

a position of one or more boundaries of the road portion.

17 . The non-transitory computer-readable medium of claim 15 , wherein the relationship is one of:

trace points in a same lane;

trace points in adjacent lanes; or

trace points in non-adjacent lanes.

18 . The non-transitory computer-readable medium of claim 15 , wherein the instructions further include instructions that when executed by the processor cause the processor to:

determine the relationship between the plurality of trace points that are within a predetermined proximity to each other.

19 . The non-transitory computer-readable medium of claim 15 , wherein the instructions further include instructions that when executed by the processor cause the processor to:

assign a first value indicating a likelihood that the relationship is trace points in a same lane based on the plurality of key points;

assign a second value indicating a likelihood that the relationship is trace points in adjacent lanes based on the plurality of key points;

assign a third value indicating a likelihood that the relationship is trace points in non-adjacent lanes based on the plurality of key points; and

determine the relationship based on the highest of the first value, the second value, and the third value.

20 . The non-transitory computer-readable medium of claim 15 , wherein the instructions further include instructions that when executed by the processor cause the processor to:

determine a trajectory for a lane based on the relationship; and

determine the characteristics of the road portion based on the trajectory.

Assignments (3)

Continuity (1)

References Cited (9)