Road Feature Georeferencing Using Tie Points and SLAM Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining geographic position data for features along roads, such as SLAM techniques combined with GPS, face inaccuracies due to GPS signal loss and drift, especially in remote areas and when vehicles turn or change elevation, leading to unreliable feature data.
Innovation Solution
A computer-implemented method that transforms relative position data from a vehicle's optical sensor into geographic coordinates by establishing a spatial relationship between the relative and geographic coordinate systems using known topographic features, allowing for accurate positioning of unmatched features through triangulation and correction points, even in areas with poor GPS signal quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If SLAM techniques with GPS are used to obtain geographic position data, then feature data can be collected along roads, but the position accuracy deteriorates due to GPS signal loss and drift
Solution Approach 1:
The patent introduces a coordinate transformation system as an intermediary between GPS/SLAM data and the map database. By transforming relative coordinate data from multiple vehicles into a common reference frame using identified common features, the system mediates the incompatible coordinate systems and achieves accurate geo-referencing without direct reliance on GPS accuracy for each individual vehicle.
Solution Approach 2:
The system uses feedback by identifying common features captured by multiple vehicles and using these features to calculate transformation parameters. The transformation parameters are then applied to correct and refine the position data, creating a feedback loop that continuously improves accuracy by comparing and adjusting data from multiple sources.
2Measurement precision
If GPS data is used to correct SLAM drift, then position accuracy improves, but the system becomes unreliable when GPS signal is lost or drifting erratically
Solution Approach 1:
The system performs self-service by using the collective data from multiple vehicles to correct individual vehicle positioning errors. Each vehicle's data contributes to the overall transformation model, and the system self-corrects drift and inaccuracies by identifying common features and calculating transformation parameters from the aggregated data without requiring continuous external GPS correction.
Solution Approach 2:
The patent merges data from multiple vehicles by identifying common features in their respective fields of view. By combining observations from multiple sources and calculating a unified transformation parameter, the system creates a more reliable and accurate position solution than any single vehicle could achieve alone, especially when GPS is unavailable.
3Quantity of substance
If multiple vehicles contribute data to improve coverage, then data quantity increases, but coordinate system compatibility and accuracy deteriorate
Solution Approach 1:
The transformation parameter calculated from common features serves a universal function for all vehicles in the network. Once the transformation parameter is derived from identified common features, it can be applied to transform position data from any vehicle's relative coordinate system into the common reference frame, making the system universally applicable across all data contributors.
Solution Approach 2:
The system changes the coordinate system parameter by calculating a transformation parameter that converts relative coordinates from multiple vehicles into a common reference frame. This parameter transformation enables accurate integration of data from multiple sources with different coordinate systems, maintaining precision while increasing data quantity.
Data Source
Figure 1
Figure 2
Figure 3A~3B
AI summary
The present invention relates to method and system for obtaining geographic position data for features that are captured through a device using a relative coordinate system, such as an optical sensor on a vehicle travelling along a route. The relative positions of the features are transformed into geographic positions by first establishing a spatial relationship between the relative coordinate system and a geographic coordinate system, for example, by comparing the route measured in the relative coordinate system to the same route measured in the geographic coordinate system by some form of satellite navigation system. Once the spatial relationship is known, it can be used to match a number of the features captured in the relative coordinate system to features having a known position within the geographic coordinate system, preferably, features that are known to have an accurately measured geographic position. The matched features can then be used as tie points between the relative coordinate system and the geographic coordinate system, which can then be used to transform unmatched features in the relative coordinate system to positions in the geographic coordinate system. For example, by triangulating two tie points and an unmatched feature in the relative coordinate system to find the angular relationship between these three relative positions, and then applying this angular relationship to the geographic positions of the tie points to identify the geographic position of the unmatched feature.