Vehicle Position Correction Using Stable Landmark Reference Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing map-based methods for vehicle localization in urban environments are inefficient and require significant computing power and time to match current images with outdated reference maps, leading to incorrect position determinations due to environmental changes and occlusions, while inertial methods suffer from position drift when GNSS signals are unavailable.
Innovation Solution
Create reference maps with stable landmarks identified over time, using georeferenced spatial information to preprocess and embed landmarks with high accuracy, allowing vehicles to correct their position using last known vectors and identified landmarks when GNSS accuracy falls below a threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If map-based methods are used to determine vehicle position by matching current images with reference maps, then position accuracy can be maintained without drift, but computational power and time requirements increase significantly
Solution Approach 1:
The patent pre-processes reference maps offline to extract and store only stable landmarks with their spatial relationships, rather than storing complete reference maps. This preliminary action reduces the computational burden during real-time vehicle localization while maintaining positioning accuracy through landmark matching.
Solution Approach 2:
The patent extracts only the essential stable landmarks from complete reference maps, separating the critical positioning elements from unnecessary map data. This extraction process reduces computational requirements by focusing only on landmarks that remain consistent over time while discarding transient or changing features.
2Speed
If inertial methods are used to determine vehicle position without GNSS signals, then position can be estimated in real-time, but position drift increases with time and distance traveled
Solution Approach 1:
The patent implements a feedback mechanism where the vehicle continuously attempts to match detected landmarks with pre-processed reference landmarks. When successful, the system corrects accumulated inertial drift by recalculating position based on landmark matching, thereby maintaining long-term positioning accuracy while preserving real-time responsiveness.
Solution Approach 2:
The patent merges inertial positioning with landmark-based positioning into a hybrid system. The inertial system provides continuous real-time position estimates, while periodic landmark matching corrections eliminate drift accumulation, combining the advantages of both methods for robust urban navigation.
3Reliability
If complete reference maps are used for vehicle localization, then comprehensive environment information is available, but matching efficiency decreases and computational time increases
Solution Approach 1:
The patent segments complete reference maps into discrete stable landmarks with their spatial relationships. Instead of matching against entire reference maps, the system matches individual landmarks, dramatically improving matching efficiency while maintaining localization reliability through the cumulative information from multiple landmarks.
Solution Approach 2:
The patent assigns different properties to different parts of the environment by identifying and marking only stable landmarks for inclusion in the processed reference data. This local quality approach focuses computational resources on reliable, unchanging features while ignoring transient elements, improving both efficiency and reliability.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure describes a method and an apparatus for determining a corrected position of a vehicle based on a stable landmark. The method includes determining a last known position vector of the vehicle; capturing an image within a vicinity of a vehicle using an imaging device; identifying a stable landmark within the captured image based on a previously constructed reference map of the vicinity of the vehicle; determining a correction for a position of the vehicle based on the determined last known position vector of the vehicle and the identified stable landmark; and determining an updated position of the vehicle based on the determined correction.