Automatic annotation of environmental features in a map during navigation of a vehicle
Among other things, we describe techniques for automatic annotation of environmental features in a map during navigation of a vehicle. The techniques include receiving, by the vehicle located within an environment, a map of the environment. Sensors of the vehicle receive sensor data and semantic data. The sensor data includes a plurality of features of the environment. A geometric model of a feature of the plurality of features is generated. The feature is associated with a drivable area within the environment. A drivable segment is extracted from the drivable area. The drivable segment is segregated into a plurality of geometric blocks, wherein each geometric block corresponds to a characteristic of the drivable area and the geometric model of the feature includes the plurality of geometric blocks. The geometric model is annotated using the semantic data. The annotated geometric model is embedded within the map.
1. A method comprising:
receiving, using one or more processors of a vehicle located within an environment, a map of the environment;
receiving, using one or more sensors of the vehicle, sensor data and semantic data, wherein the sensor data comprises 3-dimensional (3D) data;
extracting, from the sensor data, a plurality of features of the environment;
generating, from the sensor data using the one or more processors, a geometric model of a feature of plurality of features, the generating comprising:
associating, using the one or more processors, the feature with a drivable area within the environment;
extracting, using the one or more processors, at least one drivable segment from the drivable area;
segregating, using the one or more processors, based on intensity values or a color model of the 3D data, the at least one drivable segment into a plurality of geometric blocks, corresponding to characteristics of the drivable area; and
superimposing, using the one or more processors, the plurality of geometric blocks onto the 3D data to generate a polygon comprising a union of geometric blocks of the plurality of geometric blocks; and
annotating, using the one or more processors, the geometric model using the semantic data and the polygon comprising the union of geometric blocks of the plurality of geometric blocks.
2. The method of claim 1 , wherein the vehicle is located at a spatiotemporal location within the environment, and wherein the plurality of features are associated with the spatiotemporal location.
3. The method of claim 1 , wherein the feature represents a plurality of lanes of the drivable area, each lane of the plurality of lanes orientated in a same direction, and each geometric block of the plurality of geometric blocks representing a single lane of the plurality of lanes.
4. The method of claim 1 , wherein the feature represents at least one of an elevation of the drivable area, a curb located adjacent to the drivable area, or a median separating two lanes of the drivable area.
5. The method of claim 1 , wherein the drivable area comprises at least one of a road segment, a parking space located on the road segment, a parking lot connected to the road segment, or a vacant lot located within the environment.
6. The method of claim 1 , further comprising determining, using the sensor data, a spatial location of the vehicle relative to a boundary of the drivable area, the one or more sensors comprising a global navigation satellite system (GNSS) sensor or an inertial measurement unit (IMU).
7. The method of claim 1 , wherein the polygon represents a splitting of a lane of the drivable area into a plurality of lanes.
8. The method of claim 1 , wherein the polygon represents a merging of a plurality of lanes of the drivable area into a single lane.
9. The method of claim 1 , wherein the polygon represents an intersection of a plurality of lanes of the drivable area.
10. The method of claim 1 , wherein the polygon represents a roundabout comprising a spatial location on the drivable area for the vehicle to enter or exit the roundabout.
11. The method of claim 1 , wherein the polygon represents a curving of a lane of the drivable area.
12. The method of claim 1 , wherein the annotating of the geometric model comprises generating a computer-readable semantic annotation that combines the geometric model and the semantic data, the method further comprising transmitting, to a remote server or another vehicle, the map having the computer-readable semantic annotation.
13. The method of claim 1 , wherein the annotating of the geometric model using the semantic data is performed in a first mode of operation, the method further comprising navigating, using a control module of the vehicle, the vehicle on the drivable area in a second mode of operation using the map.
14. The method of claim 1 , wherein the semantic data represents at least one of a marking on the drivable area, a road sign located within the environment, or a traffic signal located within the environment.
15. The method of claim 1 , wherein the annotating of the geometric model using the semantic data comprises extracting, from the semantic data, a logical driving constraint associated with navigating the vehicle within the drivable area.
16. The method of claim 1 , wherein the 3D data is Light Detection and Ranging (LiDAR) point cloud data.
17. The method of claim 1 , wherein the color model comprises red, green, and blue (RGB) values.
18. A vehicle comprising:
one or more computer processors; and
one or more non-transitory storage media storing instructions which, when executed by the one or more computer processors, cause the one or more computer processors to:
receive a map of an environment in which the vehicle is located;
receive, using one or more sensors of the vehicle, sensor data and semantic data, wherein the sensor data comprises
3 dimensional (3D) data:
extract, from the sensor data, a plurality of features of the environment;
generate, from the sensor data, a geometric model of a feature of the plurality of the features, the generating comprising:
associating the feature with a drivable area within the environment;
extracting at least one drivable segment from the drivable area;
segregating, based on intensity values or a color model of the 3D data, the at least one drivable segment into a plurality of geometric blocks corresponding to characteristics of the drivable area; and
superimposing the plurality of geometric blocks onto the 3D data to generate a polygon comprising a union of geometric blocks of the plurality of geometric blocks; and
annotate the geometric model using the semantic data.
19. The vehicle of claim 18 , wherein the 3D data is Light Detection and Ranging (LiDAR) point cloud data.
20. The vehicle of claim 18 , wherein the color model comprises red, green, and blue (RGB) values.
21. One or more non-transitory storage media storing instructions which, when executed by one or more computing devices, cause one or more computing devices to:
receive a map of an environment that a vehicle is located within;
receive, using one or more sensors of the vehicle, sensor data and semantic data, wherein the sensor data comprises 3-dimensional (3D) data;
extract, from the sensor data, a plurality of features of the environment;
generate, from the sensor data, a geometric model of a feature of the plurality of the features, the generating comprising:
associating the feature with a drivable area within the environment;
extracting at least one drivable segment from the drivable area;
segregating, based on intensity values or a color model of the 3D data, the at least one drivable segment into a plurality of geometric blocks corresponding to characteristics of the drivable area; and
superimposing the plurality of geometric blocks onto the 3D data to generate a polygon comprising a union of geometric blocks of the plurality of geometric blocks; and
annotate the geometric model using the semantic data.
22. The one or more non-transitory storage media of claim 21 , wherein the 3D data is Light Detection and Ranging (LiDAR) point cloud data.
23. The one or more non-transitory storage media of claim 21 , wherein the color model comprises red, green, and blue (RGB) values.