Vehicle Landmark Localization for GPS Drift Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current localization systems, such as GPS, suffer from scale ambiguity and drift issues, particularly in areas with poor coverage or dense urban environments, making precise location determination challenging for vehicles.
Innovation Solution
A method for precision localization that involves detecting landmarks using a vehicle's sensor system, determining the vehicle's position relative to these landmarks, and using this information to calculate a precise global system location, which can refine or correct location estimates from secondary systems, thereby minimizing errors and providing sub-meter accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If GPS and secondary location systems are used for vehicle localization, then coverage area is extended, but measurement precision deteriorates due to scale ambiguity and drift issues
Solution Approach 1:
The patent introduces landmarks as intermediary objects with known precise locations that mediate between the vehicle's secondary location system and the global coordinate system. By detecting these landmarks and comparing observed parameters with pre-stored parameters, the system resolves scale ambiguity and corrects drift without requiring GPS coverage, thus maintaining high measurement precision across extended coverage areas
Solution Approach 2:
The system implements feedback by continuously comparing landmark parameters detected by the sensor system with pre-stored landmark parameters in the database. This comparison provides feedback information that is used to calculate correction factors for the secondary location system, thereby eliminating drift and scale ambiguity in real-time location estimates
2Measurement precision
If landmark detection and parameter extraction are performed to achieve sub-meter accuracy, then measurement precision is improved, but device complexity increases due to additional sensor systems and processing requirements
Solution Approach 1:
The patent makes the sensor system multi-functional by using it for both primary vehicle operation sensing and secondary landmark detection for localization. The same sensor system that captures images for vehicle navigation also detects landmarks, extracts their parameters, and contributes to position determination. This eliminates the need for separate dedicated landmark detection hardware, thereby reducing overall device complexity while achieving sub-meter accuracy
Solution Approach 2:
The system performs self-service by using its own sensor system and onboard processing capabilities to detect landmarks, extract parameters, and calculate correction factors without requiring external specialized equipment. The vehicle's existing computational resources are utilized to process landmark data and refine location estimates, making the high-precision localization capability self-sufficient
3Measurement precision
If real-time landmark detection and position calculation are performed continuously, then location accuracy is maintained, but use of energy increases due to continuous sensor operation and processing
Solution Approach 1:
The patent implements periodic action by triggering landmark detection and position calculation only when specific conditions are met, such as when the vehicle enters a region with pre-stored landmark data or when GPS signal availability changes. This conditional periodic operation maintains location accuracy when needed while avoiding continuous sensor activation and processing, thereby significantly reducing energy consumption compared to continuous operation
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for localization and mapping, including recording an image at a camera mounted to a vehicle, the vehicle associated with a global system location; identifying a landmark depicted in the image with a landmark identification module of a computing system associated with the vehicle, the identified landmark having a landmark geographic location and a known parameter; extracting a set of landmark parameters from the image with a feature extraction module of the computing system; determining, at the computing system, a relative position between the vehicle and the landmark geographic location based on a comparison between the extracted set of landmark parameters and the known parameter; and updating, at the computing system, the global system location based on the relative position.