Parking Space Quality Mapping for Autonomous Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately determining their position and orientation within parking garages due to the high accuracy requirements and limited detectable features and landmarks, which affects their suitability for autonomous driving.
Innovation Solution
A method to evaluate the quality of parking spaces by defining equidistant grid points within the accessible area, determining the average number of registerable features and landmarks from each point, and calculating a quality value that considers variance, occupancy status, and detector technology used, to assess suitability for autonomous driving.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the minimum number of features and landmarks is increased to meet higher accuracy requirements in parking garages, then the localization accuracy is improved, but the difficulty of detecting and measuring features increases
Solution Approach 1:
The patent applies preliminary action by pre-evaluating parking garages to determine their suitability for autonomous driving before actual operation. The system performs advance assessments including digital map creation, feature detection simulations, and quality value calculations to identify parking garages that meet minimum requirements for sufficient features and landmarks. This preliminary evaluation prevents attempting localization in unsuitable environments where the required number of features cannot be detected.
Solution Approach 2:
The system creates digital maps in advance that contain pre-identified features and landmarks with their positions and types. These digital maps are prepared before autonomous vehicles arrive, allowing the localization algorithm to have prior knowledge of where features should be located. This preliminary preparation reduces the real-time detection burden when vehicles need to determine their position and orientation.
2Reliability
If parking garages are evaluated and equipped with additional features and landmarks to improve suitability for autonomous vehicles, then the reliability of autonomous driving is improved, but the device complexity and cost increase
Solution Approach 1:
The patent performs preliminary evaluation of parking garages using existing digital maps and simulated feature detection to determine suitability before autonomous vehicles operate there. The system calculates quality values based on the number and distribution of detectable features and landmarks, identifying gaps before they become problems during actual autonomous driving operations.
Solution Approach 2:
The system provides feedback through quality values that indicate how suitable a parking garage is for autonomous driving. This feedback mechanism allows operators to understand what modifications (if any) are needed and prioritizes improvements based on actual performance metrics rather than arbitrary requirements.
3Measurement precision
If a comprehensive evaluation method with multiple parameters is used to determine quality value, then the measurement precision of parking space evaluation is improved, but the device complexity increases
Solution Approach 1:
The patent segments the evaluation process into distinct components: determining the entire accessible area, defining grid points, detecting features at each grid point, calculating the average number of features, determining variance, and computing the final quality value. This segmentation allows each component to be handled by separate modules or algorithms, making the overall complex system more manageable and implementable.
Solution Approach 2:
The system uses multiple parameters (average number of features, variance of feature distribution, occupancy status) to evaluate parking spaces, changing from a single metric to a multi-parameter assessment. This approach improves evaluation accuracy by capturing different aspects of parking garage suitability while maintaining systematic processing through defined calculation steps.
Data Source
AI summary
Systems and methods of evaluating parking spaces are provided, and in particular evaluating parking spaces in parking lots or parking garages, with regard to autonomous driving. This is accomplished by determining an accessible area of the parking space, and defining grid points in the accessible area. Features of the parking space are determined for each of the grid points, where each of the features is registrable from a respective one of the grid points. A quality value is obtained from an average number of features that is registrable from each of the grid points.