Automated road edge boundary detection
Systems, devices, products, apparatuses, and/or methods for generating a road edge boundary for an edge of a road in an AV map for controlling an autonomous vehicle on a roadway by obtaining map data associated with a map of a geographic location including a roadway associated with one or more locations of one or more vehicles in the roadway during one or more traversals of the roadway, determining one or more prediction scores based on the map data, including one or more predictions of whether the plurality of elements include road edge boundary locations, and generating in the map a road edge boundary based on the one or more prediction scores.
1. A system, comprising:
a computing system programmed to perform operations comprising:
obtaining map data associated with a map of a geographic location including a roadway, the map data describing a plurality of map elements;
obtaining vehicle data describing a location of a vehicle traversing the roadway;
determining a prediction score that indicates whether a first map element of the plurality of map elements includes a road edge boundary; and
generating a road edge boundary for a particular portion of a road in the map, the generating based at least in part on the prediction score, the generating of the road edge boundary comprising:
comparing the prediction score to one or more threshold values; and
determining that the first map element includes the road edge boundary based at least in part on the comparing.
2. The system of claim 1 , the operations further comprising, before determining the prediction score, determining that the first map element is lateral to a direction of travel of the vehicle.
3. The system of claim 1 , wherein the map data comprises an image of the geographic location including the roadway, and wherein the first map element corresponds to a pixel of the image.
4. The system of claim 3 , the pixel being associated with at least one of: an angle, a LIDAR intensity value, an attribute of the roadway, or an RGB value.
5. The system of claim 3 , the image being based at least in part on a camera image and at least in part on a LIDAR image.
6. The system of claim 3 , the operations further comprising:
obtaining sensor data generated by the vehicle while traversing the roadway; and
generating the image based on the sensor data.
7. The system of claim 1 , the operations further comprising controlling an autonomous vehicle on the roadway using the road edge boundary.
8. A computer-implemented method, comprising:
obtaining map data associated with a map of a geographic location including a roadway, the map data describing a plurality of map elements;
obtaining vehicle data describing a location of a vehicle traversing the roadway;
determining a prediction score that indicates whether a first map element of the plurality of map elements includes a road edge boundary; and
generating a road edge boundary for a particular portion of a road in the map, the generating based at least in part on the prediction score, the generating of the road edge boundary comprising:
comparing the prediction score to one or more threshold values; and
determining that the first map element includes the road edge boundary based at least in part on the comparing.
9. The computer-implemented method of claim 8 , further comprising, before determining the prediction score, determining that the first map element is lateral to a direction of travel of the vehicle.
10. The computer-implemented method of claim 8 , wherein the map data comprises an image of the geographic location including the roadway, and wherein the first map element corresponds to a pixel of the image.
11. The computer-implemented method of claim 10 , the pixel being associated with at least one of: an angle, a LIDAR intensity value, a type of attribute of the roadway, or an RGB value.
12. The computer-implemented method of claim 10 , the image being based at least in part on a camera image and at least in part on a LIDAR image.
13. The computer-implemented method of claim 10 , further comprising:
obtaining sensor data generated by the vehicle while traversing the roadway; and
generating the image based on the sensor data.
14. The computer-implemented method of claim 8 , further comprising controlling an autonomous vehicle on the roadway using the road edge boundary.
15. A non-transitory computer-readable medium comprising instructions thereon that, when executed by at least one processor, cause the at least one processor to perform operations comprising:
obtaining map data associated with a map of a geographic location including a roadway, the map data describing a plurality of map elements;
obtaining vehicle data describing a location of a vehicle traversing the roadway;
determining a prediction score that indicates whether a first map element of the plurality of map elements includes a road edge boundary; and
generating a road edge boundary for a particular portion of a road in the map, the generating based at least in part on the prediction score, the generating of the road edge boundary comprising:
comparing the prediction score to one or more threshold values; and
determining that the first map element includes the road edge boundary based at least in part on the comparing.
16. The non-transitory computer-readable medium of claim 15 , the operations further comprising, before determining the prediction score, determining that the first map element is lateral to a direction of travel of the vehicle.
17. The non-transitory computer-readable medium of claim 15 , wherein the map data comprises an image of the geographic location including the roadway, and wherein the first map element corresponds to a pixel of the image.
18. The non-transitory computer-readable medium of claim 17 , the pixel being associated with at least one of: an angle, a LIDAR intensity value, a type of attribute of the roadway, or an RGB value.
19. The non-transitory computer-readable medium of claim 17 , the image being based at least in part on a camera image and at least in part on a LIDAR image.
20. The non-transitory computer-readable medium of claim 15 , the operations further comprising controlling an autonomous vehicle on the roadway using the road edge boundary.