Vehicle Data Verification Using Clustered Digital Twins
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately verify and correct erroneous vehicle data, which can lead to undesirable vehicular actions due to sensor errors, communication failures, or other errors.
Innovation Solution
The method involves clustering vehicles with similar characteristics, comparing vehicle data with digital twins within the same cluster, verifying data when no discrepancies are found, and adjusting data when discrepancies occur.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If vehicle data is collected from multiple vehicles without verification, then data quantity and coverage are improved, but data accuracy deteriorates due to sensor errors and communication failures
Solution Approach 1:
The patent creates digital twins (virtual copies) of vehicles within clusters to compare against actual vehicle data. By generating and comparing multiple copies of vehicle data models, the system can identify and correct erroneous data while maintaining high data quantity from multiple vehicles.
Solution Approach 2:
The patent introduces digital twins as an intermediary layer between raw sensor data and processed vehicle data. This intermediary allows for indirect verification by comparing actual data against expected data patterns from digital twins, resolving the contradiction between quantity and accuracy.
2Reliability
If vehicle data is verified by comparing with digital twins, then data accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent segments the verification process by dividing vehicles into clusters based on characteristics, and further segments verification by comparing only with digital twins within the same cluster. This segmentation reduces the computational scope from comparing with all vehicles to only relevant similar vehicles, lowering overall complexity.
Solution Approach 2:
The patent applies local quality by tailoring the verification process to each vehicle cluster's specific characteristics. Each cluster has its own digital twins and verification criteria, allowing for optimized computational approaches suited to local vehicle types rather than a uniform complex system for all vehicles.
3Reliability
If vehicle data is adjusted when discrepancies are found, then data reliability is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary actions by pre-establishing digital twins and clustering vehicles before verification occurs. This preparation work is done in advance, so when actual verification is needed, the system only needs to compare against pre-existing digital twins rather than creating comparison models in real-time, reducing processing time while maintaining reliability.
Data Source
AI summary
Systems and methods for verifying vehicle data are disclosed. In one aspect, a method includes clustering a plurality of vehicle types into a plurality of vehicle clusters based at least in part on vehicle characteristics, receiving vehicle data from a vehicle, assigning the vehicle to an individual vehicle cluster of the vehicle clusters, determining one or more digital twins also assigned to the individual cluster, comparing the vehicle data of the vehicle with vehicle data associated with the one or more digital twins, verifying the vehicle data when there is no discrepancy between the vehicle data of the vehicle and the vehicle data associated with the one or more digital twins, and adjusting the vehicle data when there is a discrepancy between the vehicle data of the vehicle and the vehicle data associated with the one or more digital twins.