Composite Map Generation for Autonomous Vehicle Routing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Creating high-definition (HD) maps that cover all geographical regions and roads is costly and limited in geographic coverage, making it challenging for autonomous vehicles to operate efficiently and safely in areas without HD map information.
Innovation Solution
Generating composite maps by merging HD map data with standard definition (SD) map data, identifying corresponding nodes, and selecting candidate nodes based on routing distance similarity to create a seamless routing system that includes both HD and SD information, allowing autonomous vehicles to traverse a wider range of areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If HD maps are created to cover all geographical regions and roads, then autonomous vehicle safety and operational capability are improved, but the cost and resources required to generate the HD map increase significantly
Solution Approach 1:
The patent combines HD map data and SD map data into a composite map structure. The HD map provides high-precision routing information for covered areas, while the SD map extends geographic coverage to areas without HD mapping. This merging allows the system to achieve broad geographic coverage and acceptable safety levels without the prohibitive cost of creating complete HD maps of all regions.
Solution Approach 2:
The composite map structure applies different quality levels to different geographical regions. HD map data with high precision is used only in areas where it has been created, while SD map data provides coverage in areas without HD mapping. This local quality approach optimizes resource allocation by concentrating HD mapping efforts in high-priority areas while using SD map data for broader coverage.
2Adaptability or versatility
If HD maps are created to cover all geographical regions and roads, then autonomous vehicle operational capability is improved, but the time and cost to generate the HD map increase significantly
Solution Approach 1:
The patent merges HD map data and SD map data into a unified composite map structure that enables immediate operational capability across both HD and SD covered regions. This eliminates the time delay that would otherwise be required to wait for complete HD map coverage before deploying autonomous vehicles to new geographical areas.
Solution Approach 2:
The system performs preliminary routing calculations on the composite map structure, identifying paths that traverse both HD and SD portions. This preliminary action allows the routing engine to plan routes across the entire composite map area in advance, rather than waiting for complete HD map coverage before enabling operations.
3Area of stationary object
If composite maps are generated by merging HD map data with SD map data, then geographic coverage is expanded, but the complexity of aligning geometries and topologies from each map increases
Solution Approach 1:
The patent introduces a composite map data structure as an intermediary layer between the HD map and SD map. This composite structure includes mechanisms for matching and aligning geometries and topologies from both source maps, providing a unified interface for the routing engine while handling the complexity of integration internally.
Solution Approach 2:
The system creates a replicated composite map structure that contains references to both HD and SD map data. This copying approach allows the routing engine to operate on a unified map representation without directly manipulating the underlying HD and SD map data, simplifying the routing operations while maintaining the benefits of both map types.
4Ease of operation
If composite maps are generated by merging HD map data with SD map data, then routing capability is improved, but the difficulty of aligning geometries and topologies increases
Solution Approach 1:
The composite map data structure serves as an intermediary that handles geometry and topology alignment between HD and SD maps. It provides matching mechanisms that automatically reconcile differences in coordinate systems, road representations, and topological relationships, enabling the routing engine to operate on a unified map without directly managing alignment complexity.
Data Source
AI summary
Systems and methods for generating a composite map are provided. In one aspect, a method is provided that includes identifying a first node and a source node on a first map. The method further includes determining a candidate source node on a second map that corresponds to the source node on the first map. The method further includes determining a plurality of candidate nodes on the second map that potentially correspond to the first node and selecting a respective candidate node from the plurality of candidate nodes based on a similarity of a routing distance between: the respective candidate node and the candidate source node on the second map and the first node and the source node on the first map. The method may also include connecting the selected respective candidate node and the first node and combining the first map and the second map into a composite map.