Map Quality Assessment with Gold-Source Error Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face inaccuracies in localization and decision-making due to errors in map data, such as lateral bias and random noise, which can lead to incorrect positioning and navigation issues.
Innovation Solution
A map quality assessment system that evaluates primary map data using central computers to determine errors through methods like absolute offset, temporal and spatial inconsistencies, and user intervention likelihood, and adjusts weights based on accuracy levels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If map data is generated from telemetry data using aggregation algorithms, then map coverage and data availability are improved, but measurement precision deteriorates due to lateral bias error and random noise
Solution Approach 1:
The system implements feedback by comparing generated map data against gold source map data to determine error values. This feedback loop allows the system to identify inaccuracies in lane line positions and other map elements, enabling subsequent corrections and improvements in map data quality while maintaining broad coverage.
Solution Approach 2:
The system changes parameters by adjusting the weighting of different map data points based on their accuracy levels. High-accuracy points receive higher weights while low-accuracy points receive lower weights, effectively transforming the aggregation process to prioritize precise measurements and reduce the impact of noisy data.
2Measurement precision
If error evaluation is performed using gold source map data, then measurement precision is improved, but device complexity increases due to additional data sources and processing requirements
Solution Approach 1:
The system uses an intermediary approach by introducing a dedicated error evaluation module that mediates between the map generation process and the quality assessment process. This intermediary layer processes the comparison between generated and gold source map data, managing complexity centrally while keeping the overall system architecture modular and manageable.
3Quantity of substance
If map data points with lower accuracy are included, then map coverage is maintained, but manufacturing precision deteriorates affecting navigation reliability
Solution Approach 1:
The system applies local quality by assigning different weights to different map data points based on their individual accuracy levels. Rather than treating all data points uniformly, the system locally optimizes the contribution of each point, ensuring that high-accuracy points heavily influence the final map while low-accuracy points have minimal impact, thus maintaining both coverage and precision.
Solution Approach 2:
The system dynamically changes the parameter of data point weights based on accuracy measurements. By adjusting these weights during the aggregation process, the system maintains map completeness while ensuring that navigation calculations are driven primarily by precise measurements, thereby improving navigation reliability without sacrificing coverage.
Data Source
AI summary
A map quality assessment system that evaluates error associated with primary map data includes one or more central computers that execute instructions to determine the error associated with the primary map data, compare the error associated with the primary map data with a range of values defined by one or more quality metric values, and in response to determining the error associated with the primary map data falls within the range of values defined by the one or more quality metric values, retain a template for selecting the primary map data. In response to determining the error associated with the primary map data falls outside the range defined by the one or more quality metric values, the one or more central computers evaluate the primary map data for real-life anomalies within one or more roadways represented by the primary map data.