Procedural world generation using tertiary data
Procedural world generation using tertiary data is described. In an example, a computing device can receive road network data associated with the real environment and a road mesh associated with a real environment. The computing device can associate the road network data with the road mesh to generate a simulated environment. Additionally, the computing device can associate supplemental data with the road network data and the road mesh to enhance the simulated environment (e.g., supplementing information otherwise unavailable to the sensor data due to an occlusion). The computing device can output the simulated environment for at least one of testing, validating, or training an algorithm used by an autonomous robotic computing device for at least one of navigating, planning, or decision making.
1. A system comprising:
one or more processors; and
one or more non-transitory computer readable media storing computer executable instructions that, when executed, cause the one or more processors to perform operations comprising:
aligning, as a first alignment, a first region associated with a road mesh and a second region associated with supplemental data associated with a simulated environment;
determining, based at least in part on the first alignment, an error between the road mesh and the supplemental data;
based at least in part on the error, performing at least one of:
blending the road mesh and the supplemental data to generate blended data to reduce the error; or
deforming the road mesh to substantially align, as a second alignment, the road mesh with the supplemental data, wherein the second alignment is different form the first alignment; and
outputting, based at least in part on the blending or the deforming, a modified simulated environment for use by an autonomous robotic computing device.
2. The system as claim 1 recites, wherein the supplemental data comprises a geospatial file format including elevation data.
3. The system as claim 1 recites, wherein the error comprises at least one of: a single measurement, an average of multiple measurements, a maximum over an area, a minimum over an area, or a total error representative of a difference between a first portion of the road mesh and a second portion of the supplemental data.
4. The system as claim 1 recites, wherein:
the operations further comprise comparing the error to a threshold amount of error, and
performing at least one of:
the blending is further based at least in part on the error not exceeding the threshold amount of error, or
the deforming is based at least in part on the error meeting or exceeding the threshold amount of error.
5. The system as claim 1 recites, wherein the operations further comprise generating a modified simulated environment based at least in part on the blending or the deforming.
6. The system as claim 1 recites, wherein the error is a vertical distance error or a horizontal distance error.
7. The system as claim 1 recites, wherein the error comprises an error between a first portion of the road mesh and a second portion of the supplemental data.
8. A computer-implemented method comprising:
aligning, as a first alignment, a first region associated with a road mesh and a second region associated with supplemental data associated with a simulated environment;
determining, based at least in part on the first alignment, an error between the road mesh and the supplemental data; and
based at least in part on the error, performing at least one of:
blending the road mesh and the supplemental data to generate blended data to reduce the error; or
deforming the road mesh to substantially align, as a second alignment, the road mesh with the supplemental data, wherein the second alignment is different form the first alignment; and
outputting, based at least in part on the blending or the deforming, a modified simulated environment for use by an autonomous robotic computing device.
9. The computer-implemented method as claim 8 recites, wherein the supplemental data comprises a geospatial file format including elevation data.
10. The computer-implemented method as claim 8 recites, wherein the simulated environment is associated with a real environment determined from sensor data from at least one data collection device.
11. The computer-implemented method as claim 8 recites, wherein the road mesh comprises a plurality of three-dimensional tiles.
12. The computer-implemented method as claim 8 recites, wherein:
further comprising comparing the error to a threshold amount of error, and performing at least one of:
the blending is further based at least in part on the error not exceeding the threshold amount of error, or
the deforming is based at least in part on the error meeting or exceeding the threshold amount of error.
13. The computer-implemented method as claim 8 recites, wherein determining the error between the road mesh and the supplemental data comprises periodically measuring the error between the road mesh and the supplemental data to determine an average of multiple measurements, a maximum over an area, or a minimum over an area.
14. The computer-implemented method as claim 8 recites, wherein:
measuring the error comprises measuring the error in a designated position within the road mesh, and
the designated position comprises a road centerline.
15. The computer-implemented method as claim 8 recites, wherein the blending comprises at least one of: global blending, local blending, linear blending, smooth curve blending to blend the road mesh and the supplemental data.
16. The computer-implemented method as claim 8 recites, wherein a level of blending is based at least in part on a distance between a centerline of the road mesh and an area of the supplemental data.
17. The computer-implemented method as claim 8 recites, further comprising smoothing a transition between a boundary of the road mesh and a boundary of the supplemental data.
18. The computer-implemented method as claim 8 recites, wherein the supplemental data comprises elevation data collected by a third-party source or system.
19. The computer-implemented method as claim 8 recites, wherein the supplemental data comprises a geospatial file format that is associated with a United States Geological Survey (USGS) Data Evaluation Model (DEM) standard.
20. The computer-implemented method as claim 8 recites, wherein the supplemental data provides information associated with a real environment that is otherwise unavailable to at least one data collection device due to at least one occlusion.