Systems and methods for estimating lane boundaries using a slicing model

A non-transitory computer-readable medium comprising:

• instructions that when executed by a processor cause the processor to:
• compute three-dimensional (3D) representations that are discretized from acquired data about road edges associated with driving lanes for a road;
• derive discrete and lateral slices of the road edges using a slicing model, wherein the road edges are connected in a road graph that describes a mapped area, and the lateral slices comprising different channels with keypoints that expand information for an area on the road;
• extract features from the lateral slices and the different channels individually using a neural model for forming a histogram to estimate lane boundaries about the driving lanes;
• and
• generate a map by linking the lane boundaries individually along the road edges.

A method comprising:

• computing three-dimensional (3D) representations that are discretized from acquired data about road edges associated with driving lanes for a road;
• deriving discrete and lateral slices of the road edges using a slicing model, wherein the road edges are connected in a road graph that describes a mapped area, and the lateral slices comprising different channels with keypoints that expand information for an area on the road;
• extracting features from the lateral slices and the different channels individually using a neural model for forming a histogram to estimate lane boundaries about the driving lanes;
• and
• generating a map by linking the lane boundaries individually along the road edges.