| CPC G01S 7/4802 (2013.01) [G01S 17/89 (2013.01); G01S 17/931 (2020.01); G06V 10/82 (2022.01); G06V 20/182 (2022.01)] | 20 Claims |
|
1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause the system to perform operations comprising:
receiving LiDAR data representative of a portion of an environment, the LiDAR data including intensity information of LiDAR returns from the portion of the environment;
identifying a subset of the LiDAR data having an elevation greater than a threshold distance from a ground plane;
generating filtered LiDAR data excluding the subset of the LiDAR data;
associating intensity information of LiDAR returns associated with the filtered LiDAR data with a voxel space representing the portion of the environment;
determining, based on aggregated intensity information in voxels of the voxel space, image data representing a top-down view of the voxel space;
inputting the image data into a machine-learned (ML) model;
receiving, as an output of the ML model, classification information comprising a classification associated with individual pixels of the image data, wherein the classification is indicative of a road map element of a set of road map elements;
determining, based at least in part on the classification information, a segment of the image data corresponding to a first road map element of the set of road map elements, the first road map element corresponding to an element on a driving surface; and
generating, based at least in part on the segment of the image data, a road network map of the environment, wherein a vehicle is localized in the environment based at least in part on the road network map.
|