System and method for generating a semantic map for a road
Systems, methods, and other embodiments described herein relate to generating a semantic map for a road segment. In one embodiment, a method includes receiving sensor data related to a road segment, generating an orthogonal axis related to the road segment, and projecting the sensor data onto the orthogonal axis. The method includes generating a range of weighting functions based on potential characteristics of the road segment and determining a plurality of scores based on applying the range of weighting functions to the sensor data along the orthogonal axis. The method includes selecting one weighting function from the range of weighting functions based on one score of the plurality of scores, where the one score is a highest score. The method includes determining characteristics of the road segment based on the selected weighting function.
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 segment, the sensor data including trace points and key points and the road segment being a portion of a road;
aggregate the sensor data into a common reference system such that relationships between the trace points and the key points are consistent;
generate an orthogonal axis related to the road segment;
project the sensor data onto the orthogonal axis;
generate a range of weighting functions based on lane number-lane width configurations associated with the road and based on lane number-lane width configurations associated with a second road segment, the second road segment neighboring the road segment;
determine a plurality of scores based on applying the range of weighting functions to the sensor data along the orthogonal axis;
select a subset of weighting functions from the range of weighting functions based on one score of the plurality of scores, the one score being a highest score; and
determine characteristics of the road segment based on the subset of weighting functions, the characteristics of the road segment including a width of one or more lanes in the road segment.
2 . The system of claim 1 , wherein the characteristics of the road segment include at least one of:
number of lanes in the road segment;
a position of one or more lane markings on the road segment; or
a position of one or more boundaries of the road segment.
3 . The system of claim 1 , wherein the sensor data is generated from a plurality of vehicle sensors.
4 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:
divide the road into a plurality of road segments based on a curve of the road, wherein the plurality of road segments includes the road segment.
5 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:
generate the range of weighting functions based on historical information.
6 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:
generate the range of weighting functions based on characteristics of an environment of the road segment.
7 . The system of claim 1 , wherein the machine-readable instructions further include instructions that when executed by the processor cause the processor to:
generate the range of weighting functions based on characteristics of a neighboring road segment.
8 . A method comprising:
receiving sensor data related to a road segment, the sensor data including trace points and key points and the road segment being a portion of a road;
aggregating the sensor data into a common reference system such that relationships between the trace points and the key points are consistent;
generating an orthogonal axis related to the road segment;
projecting the sensor data onto the orthogonal axis;
generating a range of weighting functions based on lane number-lane width configurations associated with the road and based on lane number-lane width configurations associated with a second road segment, the second road segment neighboring the road segment;
determining a plurality of scores based on applying the range of weighting functions to the sensor data along the orthogonal axis;
selecting a subset of weighting functions from the range of weighting functions based on one score of the plurality of scores, the one score being a highest score; and
determining characteristics of the road segment based on the subset of weighting functions, the characteristics of the road segment including a width of one or more lanes in the road segment.
9 . The method of claim 8 , wherein the characteristics of the road segment include at least one of:
number of lanes in the road segment;
a position of one or more lane markings on the road segment; or
a position of one or more boundaries of the road segment.
10 . The method of claim 8 , wherein the sensor data is generated from a plurality of vehicle sensors.
11 . The method of claim 8 , further comprising:
dividing the road into a plurality of road segments based on a curve of the road, wherein the plurality of road segments includes the road segment.
12 . The method of claim 8 , further comprising:
generating the range of weighting functions based on historical information.
13 . The method of claim 8 , further comprising:
generating the range of weighting functions based on characteristics of an environment of the road segment.
14 . The method of claim 8 , further comprising:
generating the range of weighting functions based on characteristics of a neighboring road segment.
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 segment, the sensor data including trace points and key points and the road segment being a portion of a road;
aggregate the sensor data into a common reference system such that relationships between the trace points and the key points are consistent;
generate an orthogonal axis related to the road segment;
project the sensor data onto the orthogonal axis;
generate a range of weighting functions based on lane number-lane width configurations associated with the road and based on lane number-lane width configurations associated with a second road segment, the second road segment neighboring the road segment;
determine a plurality of scores based on applying the range of weighting functions to the sensor data along the orthogonal axis;
select a subset of weighting functions from the range of weighting functions based on one score of the plurality of scores, the one score being a highest score; and
determine characteristics of the road segment based on the subset of weighting functions, the characteristics of the road segment including a width of one or more lanes in the road segment.
16 . The non-transitory computer-readable medium of claim 15 , wherein the characteristics of the road segment include at least one of:
number of lanes in the road segment;
a position of one or more lane markings on the road segment; or
a position of one or more boundaries of the road segment.
17 . The non-transitory computer-readable medium of claim 15 , wherein the sensor data is generated from a plurality of vehicle sensors.
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:
divide the road into a plurality of road segments based on a curve of the road, wherein the plurality of road segments includes the road segment.
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:
generate the range of weighting functions based on historical information.
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:
generate the range of weighting functions based on characteristics of a neighboring road segment.