Map Object Association with Road Links for Autonomous Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional digital maps and navigation systems are overwhelmed by vast amounts of data, particularly when providing dynamic route guidance and driver assistance, as they often lack efficient methods to utilize information about objects proximate to road links unless a specific destination is selected, leading to ineffective use of data for autonomous or semi-autonomous vehicle control.
Innovation Solution
A method and apparatus that determine a sequence of road links likely to be traversed by a vehicle, identify objects within a predefined distance of these links, generate object profiles including object type, location, and geometry, and provide driver assistance instructions such as location referencing, lane assistance, or emergency braking, based on these profiles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If conventional digital maps provide all available data about objects within an area, then completeness of information is improved, but data processing complexity and system overload increase
Solution Approach 1:
The patent segments the road network into discrete road links and categorizes objects by type (e.g., pedestrians, vehicles, cyclists) and distance zones. This segmentation allows the system to process only relevant object data for each road link rather than processing all objects in the entire map area, reducing data processing complexity while maintaining information completeness for navigation decisions.
Solution Approach 2:
The patent applies local quality by creating object profiles with different levels of detail based on their relevance to the current road link. Objects closer to the vehicle's path receive more detailed processing, while distant or less relevant objects are processed with less detail. This selective processing reduces overall system complexity while preserving critical information.
2Loss of information
If the system processes all objects within a large area, then object detection completeness is improved, but processing time increases
Solution Approach 1:
The patent divides the processing area into distance-based zones around each road link and processes objects in segments based on their distance and relevance. This segmented approach allows the system to quickly identify and process only those objects that fall within relevant zones, significantly reducing processing time compared to analyzing all objects in the entire map area while maintaining detection completeness for objects that matter.
Solution Approach 2:
The patent implements partial action by processing only the subset of objects that are relevant to the current road link and vehicle context, rather than processing all objects exhaustively. This selective processing achieves sufficient detection completeness for navigation purposes without the time cost of complete processing.
3Loss of information
If the system stores detailed information for all objects, then data completeness is improved, but memory requirements and data management complexity increase
Solution Approach 1:
The patent applies local quality by creating object profiles with varying levels of detail based on the object's relevance to the current road link. Critical attributes are stored for all objects, but detailed geometric and contextual information is stored only for objects within relevant distance zones or of high importance. This reduces overall data volume while maintaining completeness of essential information.
Solution Approach 2:
The patent extracts and stores only the essential attributes needed for navigation and safety decisions in the object profiles, rather than storing all available data about each object. By extracting only the most relevant information (object type, distance, basic geometry, relevance flags), the system maintains data completeness for decision-making while significantly reducing the total quantity of stored data.
Data Source
AI summary
Embodiments described herein may provide a method for identifying objects along a path established though the Electronic Horizon. An apparatus is provided to facilitate autonomous or semi-autonomous control of a vehicle, where the apparatus is caused to: determine, within a road network, a sequence of road links that satisfy a predetermined likelihood of being traversed by a vehicle, where the road network is segmented into tiles in a map data service provider database; receive, in response to determining the sequence of road links, one or more tiles corresponding to the sequence of road links; search within the one or more tiles for objects within a predetermined distance of the sequence of road links; and generate an object profile for each object, where the object profile includes information relating to the respective object and a distance of the respective object from the road link.