Vehicle Map Updates Using Road Topography Feature Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the sheer volume of data needed for map storage and updates, which can limit or adversely affect navigation efficiency.
Innovation Solution
A system and method for updating vehicle navigation maps using drive information from vehicles, including detected road edges, lane marks, and road signs, processed by a trained model to generate and distribute updated road topography features to host vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional mapping technology is used to store and update map data, then navigation functionality is provided, but the sheer volume of data needed to store and update the map poses daunting challenges and adversely affects navigation efficiency
Solution Approach 1:
The patent extracts only the essential road topography features (lane markings, road edges, signs, signals, curbs) from complete map data, storing and updating only these critical navigation elements rather than entire map datasets. This reduction in data volume directly addresses the contradiction by maintaining navigation reliability through feature extraction while improving productivity by reducing storage and update burdens
Solution Approach 2:
The patent segments map data into discrete road topography features (lane markings, road edges, signs, signals, curbs) that can be independently detected, stored, and updated. This segmentation allows the system to manage and update only specific feature portions rather than entire maps, resolving the contradiction between maintaining accurate navigation data and improving navigation efficiency through reduced data processing
2Loss of information
If complete map data is stored and updated for autonomous navigation, then comprehensive navigation information is available, but the sheer quantity of data limits or adversely affects autonomous navigation
Solution Approach 1:
The system extracts only the necessary road topography features required for autonomous navigation (lane markings, road edges, signs, signals, curbs) from complete map data. This extraction maintains the essential navigation information needed for safe operation while dramatically reducing the data volume, thereby preventing information loss of critical features while improving autonomous navigation efficiency
Solution Approach 2:
The patent applies local quality by focusing storage and update resources on specific road topography features that are locally relevant to navigation needs rather than storing uniform complete map data everywhere. This approach ensures that only the quality and detail necessary for each specific feature type is maintained, reducing overall data quantity while preserving navigation-critical information
Data Source
AI summary
The embodiments of the present disclosure relate to a system for updating a map for use in navigating a host vehicle relative to a road segment. The system may comprise a processor configured to receive drive information from a vehicle, provide a representation of the drive information to a trained neural network configured to provide an output that includes identification of an update to make to a road topography feature representation stored in the map; generate an updated road topography feature representation in response to the identification of the update to make to the road topography feature representation; and distribute the updated map to at least one host vehicle navigation system for use in navigating the host vehicle along the road segment relative to the updated road topography feature representation.