Elevation-Aware Traversable Maps for Autonomous Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map data for autonomous vehicles inaccurately combines drivable surfaces that are vertically separated, leading to inefficient and potentially unsafe vehicle operations, such as unnecessary maneuvers to avoid non-interacting paths.
Innovation Solution
Incorporating elevation information to determine and merge drivable surfaces based on shared elevation layers, while separating those on different layers, and generating updated map data that accurately represents total drivable areas, including non-standard surfaces like parking lots and junctions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If map data combines all drivable surfaces without elevation information, then the map coverage is complete, but the accuracy of drivable area representation deteriorates by merging vertically separated surfaces
Solution Approach 1:
The patent introduces elevation information as a third dimension to differentiate drivable surfaces that overlap in 2D space. By incorporating elevation layers, the system can distinguish between surfaces at different heights (e.g., ground level vs. overpasses), preventing incorrect merging while maintaining complete surface coverage in the updated map data.
2Measurement precision
If map data includes detailed elevation information for all surfaces, then the accuracy of navigation improves, but the complexity of map data processing increases
Solution Approach 1:
The patent segments drivable surfaces into distinct elevation layers, organizing the map data by vertical strata. This segmentation allows the system to process and query surfaces at each elevation level independently, reducing the computational complexity of determining which surfaces are actually traversable from a given position while maintaining high navigation accuracy.
3Productivity
If the vehicle uses traditional 2D map data without elevation layers, then the system complexity is low, but the vehicle performs unnecessary maneuvers to avoid non-intersecting paths
Solution Approach 1:
The patent introduces elevation layers as an intermediary data structure between the 2D map representation and the vehicle's navigation decisions. This intermediary layer provides the necessary vertical context to distinguish between intersecting and non-intersecting paths without requiring complex 3D modeling, thereby improving operational efficiency while maintaining relative simplicity in the overall system architecture.
Data Source
AI summary
Techniques are provided comprising receiving map data and determining a first polygon representing a first traversable surface and a second polygon representing a second traversable surface. The first polygon may include a first portion that overlaps with a second portion of the second polygon. The techniques may determine, based at least in part on elevation information associated with the first traversable surface and the second traversable surface, respective elevation layers associated with the first polygon and the second polygon. It may be determined whether to merge the first polygon and the second polygon based at least in part on whether the first polygon is associated with a same elevation layer as the second polygon. Based at least in part on determining whether to merge the first and second polygons, an updated map may be determined.