Vehicle Trace Mapping to Road Graphs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing road graph representations lack essential information such as road elevation and directionality, leading to mapping inconsistencies and incorrect associations of vehicle sensor data, which can result in navigation errors and safety hazards.
Innovation Solution
A system that maps vehicle trace frames to the nearest portion of a road graph, identifies mapping inconsistencies, and associates vehicle sensor data with the correct segments of the road graph, thereby resolving inconsistencies and enhancing the accuracy of road graph representations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If road graph representations include more information detail, then navigation and autonomous driving capability is improved, but mapping inconsistency and data association errors increase
Solution Approach 1:
The patent segments the road graph into multiple sections or segments, allowing different levels of information detail to be applied to different segments. This enables comprehensive information representation in areas where it is reliable while maintaining mapping consistency by using standardized segmentation approaches across the entire road network.
Solution Approach 2:
The patent introduces an intermediary processing layer that mediates between raw road information and the final road graph representation. This intermediary layer validates, standardizes, and reconciles incoming data before integrating it into the road graph, preventing mapping inconsistencies while preserving essential information detail.
2Measurement precision
If vehicle sensor data is associated with road graph portions, then navigation accuracy is improved, but mapping inconsistencies cause incorrect associations
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously validates vehicle sensor data associations with the road graph. When inconsistencies are detected, the system adjusts associations based on feedback from multiple data sources and validation rules, ensuring that sensor data is correctly associated with the appropriate road graph portions despite initial mapping inconsistencies.
Solution Approach 2:
The patent performs preliminary validation and reconciliation of road graph data before associating vehicle sensor data. By pre-processing the road graph to identify and resolve potential mapping inconsistencies beforehand, the system ensures that sensor data associations are made to accurate and reliable road graph portions.
Data Source
AI summary
Systems, methods, and other embodiments described herein relate to associating vehicle sensor data with road graphs. In one embodiment, a system includes a processor and a memory storing machine-readable instructions. The machine-readable instructions, when executed by the processor, cause the processor to 1) map frames of a vehicle trace along a road to a respective nearest portion of a road graph for the road, 2) identify, as a non-baseline segment, a portion of the road graph for which there is a mapping inconsistency, and 3) for a baseline segment, associate vehicle sensor data captured at the frames with the respective nearest portion of the road graph.