Feature Data Collection Apparatus Using Reliability Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately and efficiently collecting data for map features, as the speed and sufficiency of data collection vary by feature and environment, making it difficult to determine the optimal timing for stopping data collection for each feature.
Innovation Solution
An apparatus that uses a probability distribution of reliability to indicate the likelihood of a feature's existence as a function of position, updating this distribution based on received feature data and transmitting instructions to stop data collection when the reliability distribution meets a predetermined threshold.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If feature data is collected continuously for each feature, then measurement precision of feature position is improved, but loss of time and communication load increase
Solution Approach 1:
The system uses a probability distribution of reliability as feedback to dynamically determine when to stop collecting feature data. The reliability distribution is updated with each new data point, and collection stops when the distribution indicates sufficient precision has been achieved, avoiding continuous collection without end conditions.
Solution Approach 2:
The system changes the parameter of collection timing from fixed/continuous to dynamic based on reliability threshold. By monitoring the probability distribution of reliability and comparing it against predetermined thresholds, the system adjusts collection duration adaptively for each feature based on actual data quality.
2Measurement precision
If feature data is collected continuously for each feature, then measurement precision of feature position is improved, but device complexity increases
Solution Approach 1:
The reliability distribution serves as an automated feedback mechanism that eliminates the need for complex manual control systems. The system automatically monitors data quality through the probability distribution and makes decisions about when to stop collection based on predetermined thresholds, reducing control complexity.
Solution Approach 2:
The system performs self-evaluation of data quality through the probability distribution of reliability. Each new data point automatically updates the distribution, and the system self-determines when collection should stop based on whether the reliability threshold is met, eliminating the need for external complex control systems.
3Loss of time
If data collection stops when reliability threshold is met, then loss of time is reduced, but reliability of positional accuracy may be insufficient
Solution Approach 1:
The system uses dynamically updated probability distribution parameters (mean and variance) to make informed decisions about stopping collection. By continuously monitoring whether the variance falls below the threshold or the mean reliability exceeds the threshold, the system ensures sufficient accuracy before stopping.
Solution Approach 2:
The reliability distribution provides continuous feedback on data quality, allowing the system to stop collection only when sufficient reliability is demonstrated. The feedback loop ensures that stopping decisions are based on actual data quality metrics rather than arbitrary time limits.
4Productivity
If feature data is collected from multiple vehicles, then productivity of map updates is improved, but loss of information about data quality increases
Solution Approach 1:
The system maintains the probability distribution of reliability as feedback information even when collecting from multiple vehicles. This allows the system to track data quality across multiple data sources and make informed decisions about when each feature's collection should stop, preventing loss of quality information during parallel collection.
Data Source
AI summary
An apparatus for collecting feature data includes a memory configured to store map information including a probability distribution of reliability indicating how likely a feature related to travel of vehicles exists as a function of position; and one or more processors configured to store feature data indicating the position of the feature in the memory whenever receiving the feature data from any of one or more vehicles via a communication circuit, update the probability distribution of reliability indicating how likely the feature exists as a function of position, based on the position of the feature indicated by each of one or more pieces of received feature data, and transmit an instruction to stop collecting the feature data to the one or more vehicles via the communication circuit for a feature regarding which the extent of the updated probability distribution is not greater than a predetermined threshold.