Driving Assistance System Stop Position Estimation Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driving assistance systems face inaccuracies in estimating target stop positions due to variations in driving behaviors among individual drivers, leading to inconsistencies in aggregated stop position information.
Innovation Solution
A driving assistance system that integrates travel information from multiple vehicles, estimates a target stop position, and eliminates data from drivers with low convergence properties to improve accuracy by using a center that communicates with vehicles, processes travel data, and generates assistance information based on excellent driving features.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If stop position information from all vehicles is aggregated without filtering, then the quantity of data increases, but the accuracy of estimating target stop position deteriorates due to variations in driving behavior
Solution Approach 1:
The patent extracts and eliminates stop position information from vehicles whose driving behavior does not converge to the average behavior pattern. By removing these outlier data points while retaining the majority of aggregated data, the system maintains sufficient data quantity while improving estimation accuracy through selective extraction of relevant information.
Solution Approach 2:
The patent applies different quality standards to different data points based on their convergence properties. Instead of uniformly treating all stop position information, the system evaluates each vehicle's driving behavior convergence and selectively includes or excludes its data, thereby improving overall data quality while maintaining adequate quantity for accurate estimation.
2Measurement precision
If strict filtering criteria are applied to eliminate low-convergence data, then the accuracy of target stop position estimation improves, but the loss of information increases due to elimination of valid stop position data
Solution Approach 1:
The patent changes the evaluation parameter from binary inclusion/exclusion to a convergence-based continuous assessment. By measuring how closely each vehicle's driving behavior converges to the average pattern, the system can make informed decisions about data inclusion, thereby minimizing information loss while maintaining high estimation accuracy through parameter-based differentiation.
3Productivity
If all stop position information is used for aggregation, then the productivity of the system is maintained, but the reliability of the target stop position estimation deteriorates due to inconsistent driving behaviors
Solution Approach 1:
The patent extracts and removes stop position information from vehicles with non-convergent driving behavior before aggregation. This pre-filtering approach maintains processing efficiency by eliminating problematic data early in the workflow, while simultaneously improving reliability by ensuring that only consistent, high-quality data contributes to the final target stop position estimation.
Solution Approach 2:
The patent implements a feedback mechanism where the system evaluates driving behavior convergence and uses this evaluation to determine which data points to include in aggregation. This feedback loop ensures that only reliable data from vehicles with consistent driving patterns is processed, thereby maintaining both productivity and reliability in the target stop position estimation.
Data Source
AI summary
A system for assisting vehicle driving includes a processor executing a process of assisting vehicle driving; and a memory. The process includes communicating with vehicles to obtain the travel information, storing the travel information in the memory; estimating a target stop position where the vehicle should stop based on the travel information; transmitting the target stop position to the vehicles-obtaining an index indicating at least one of repeatability of driving behavior of a driver, proximity of the behavior to an average value of others, and fuel consumption, determining a first driver corresponding to the index indicating a value less than a value determined based on the travel information of others; and eliminating a stop position information form the travel information stored in the memory, the stop position information indicating a stop position based on the travel information of the vehicle driven by the first driver.