Inferring Static Traffic Artifacts From Aggregated GPS Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current navigation systems fail to account for static traffic artifacts like traffic lights, school zones, and railroad crossings, leading to misleading routing assistance and potential hazards for drivers.
Innovation Solution
A method and system that utilize aggregated data from GPS devices to infer the presence, location, and specifics of static traffic artifacts, including traffic lights, school zones, and railroad crossings, by analyzing metrics such as stop patterns and travel data, and update geographic information systems with this information for improved navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If navigation systems use traditional routing methods without considering static traffic artifacts, then the routing calculation is simple and fast, but the routing accuracy and reliability deteriorate leading to misleading assistance
Solution Approach 1:
The system enables GPS devices to automatically collect session data during normal operation, autonomously identify stop patterns indicating traffic artifacts, and contribute this data to the repository without requiring manual input or specialized hardware. Each device serves itself and the collective system through its normal navigation usage.
Solution Approach 2:
A centralized artifact repository acts as an intermediary between individual GPS devices and the navigation system. The repository aggregates session data from multiple devices, processes stop pattern analysis, and generates traffic artifact information that is then distributed back to devices, mediating the complexity between individual users and the collective intelligence.
2Reliability
If navigation systems account for static traffic artifacts like traffic lights and school zones, then the routing reliability improves, but the device complexity increases due to additional data processing requirements
Solution Approach 1:
The system segments the complex task of traffic artifact detection into two distinct parts: (1) individual GPS devices perform simple session data collection and stop pattern identification, and (2) a centralized repository performs aggregate analysis and artifact generation. This segmentation distributes computational complexity away from individual devices.
Solution Approach 2:
The system merges data from multiple GPS devices into a centralized repository, combining session data from numerous sources to collectively identify traffic artifacts. This merging approach pools computational resources and data samples, reducing the processing burden on any single device while improving detection accuracy.
3Measurement precision
If the system collects and processes session data from multiple GPS devices to identify traffic artifacts, then the measurement precision of artifact location improves, but the loss of time for data aggregation increases
Solution Approach 1:
GPS devices perform preliminary data collection during their normal operation, continuously gathering session data and identifying stop patterns as they occur. This preliminary action prepares data in advance, so when aggregation is needed, the foundation work is already completed, reducing the time penalty for collective analysis.
Solution Approach 2:
The system maintains continuous data collection from GPS devices during their normal navigation use, without interrupting their primary function. Session data is gathered continuously as devices operate, and the repository continuously processes incoming data, ensuring that useful action (data collection and analysis) occurs without interruption or significant time loss.
Data Source
AI summary
Aggregated navigation system data can be used by an artifact repository to infer the presence of a static traffic artifact. Static traffic artifact can include traffic lights, traffic signs, special traffic zones, railroad crossings, and the like. Metric data collected from multiple global positioning systems (GPS) devices can provide sampling data for inferring a static traffic artifact on a road. Metrics can include driving behavior, travel direction, velocity, timestamps, delay, and the like. For example, if thirty percent of the data collected about an intersection indicates drivers come to a stop at an intersection, the system can infer a traffic light exists at the intersection. Each traffic artifact can have an associated confidence factor which can indicate the degree of accuracy of the inferred artifact. Confidence factor can be increased or decreased based on the re-evaluation of sample data for the artifact.