Cloud Road Hazard Database Accuracy Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current connected vehicle technologies face challenges in accurately detecting and sharing road hazards due to variations in sensor performance and data accuracy, leading to mixed and noisy data being shared among vehicles.
Innovation Solution
A system and method for updating a cloud-based road anomaly database by receiving information from vehicles, comparing detected object data against stored data, and determining an accuracy score to select and update the database with higher accuracy data, ensuring accurate road hazard information is shared and stored.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If data from multiple vehicles is collected and shared in a cloud-based database, then the quantity of road hazard data increases, but the accuracy and reliability of the data decreases due to variations in sensor performance and detection capabilities
Solution Approach 1:
The patent applies parameter changes by transforming raw detection data into standardized data with associated accuracy scores. The system changes the parameters of the data by normalizing detection results from different sensor types and vehicles, assigning confidence levels based on sensor performance characteristics, and filtering data based on predefined accuracy thresholds. This allows the database to maintain high accuracy while accumulating data from multiple vehicles with varying sensor capabilities
Solution Approach 2:
The cloud-based platform acts as an intermediary that mediates between multiple vehicles with different sensor performances and the final hazard database. The platform receives raw detection data from various vehicles, processes and standardizes the data through normalization and confidence scoring, and outputs filtered high-quality data. This intermediary processing layer resolves the contradiction by decoupling the quantity of received data from the quality of stored data
2Loss of information
If all detected road hazards are shared among vehicles, then the completeness of hazard information improves, but the noise and false detection results increase due to low-accuracy sensors
Solution Approach 1:
The system applies parameter changes by transforming raw detection data into standardized data with associated accuracy scores. The system changes the parameters of the data by normalizing detection results from different sensor types and vehicles, assigning confidence levels based on sensor performance characteristics, and filtering data based on predefined accuracy thresholds. This allows the database to maintain high accuracy while accumulating data from multiple vehicles with varying sensor capabilities
Solution Approach 2:
The patent applies the extraction principle by selectively removing low-quality data from the dataset. The system extracts only those detection results that meet predefined accuracy thresholds and confidence level requirements. By taking out and excluding noisy or unreliable detections from vehicles with poor sensor performance, the system maintains completeness of valid hazard information while eliminating false positives and noise from the shared database
3Area of stationary object
If data from vehicles with various sensor suites is aggregated, then the coverage of detected hazards improves, but the reliability of the aggregated data decreases due to skewed sensor performance over time
Solution Approach 1:
The system applies parameter changes by transforming raw detection data into standardized data with associated accuracy scores. The system changes the parameters of the data by normalizing detection results from different sensor types and vehicles, assigning confidence levels based on sensor performance characteristics, and filtering data based on predefined accuracy thresholds. This allows the database to maintain high accuracy while accumulating data from multiple vehicles with varying sensor capabilities
Solution Approach 2:
The patent applies local quality by treating data from different vehicles and sensors with different quality standards. Instead of applying a uniform acceptance criterion to all data, the system evaluates each detection based on the specific vehicle's sensor performance characteristics, detection conditions, and historical accuracy. This allows the system to maintain high overall reliability while incorporating diverse data sources with varying local qualities
Data Source
AI summary
A system comprising at least one hardware processor for updating a cloud-based road anomaly database is disclosed, wherein the system receives information from a vehicle regarding an object detected by one or more sensors of the vehicle, the information may include a location and/or a size of the detected object; compares the location and/or the size of the first detected object against data stored in a road feature database regarding the first detected object; determines, based on comparing the location and/or the size, an accuracy score associated with the first detected object and the second detected object; and updates the cloud-based road anomaly database with the received information for the second detected object based on the associated accuracy score being higher than at least one of a threshold accuracy score or an accuracy score associated with corresponding object information stored in the cloud-based road anomaly database.