Map Tile Traffic Prediction Using Current And Historical Probe Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigation systems lack accurate and real-time traffic prediction capabilities, particularly for autonomous vehicles, leading to inefficiencies and wasted time due to congestion caused by various factors such as weather, construction, and incidents.
Innovation Solution
A system that generates a Tile-Based Traffic Index (TTI) by aggregating current and historical traffic data from probe vehicles and map attributes to predict traffic conditions, providing confidence values and delivering traffic information within a defined radius.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If real-time traffic data is collected and analyzed, then navigation accuracy is improved, but system complexity and data processing requirements increase
Solution Approach 1:
The system divides the service area into discrete map tiles, each independently processed and cached. This segmentation allows the system to handle large geographic areas without processing all data centrally, reducing overall system complexity while maintaining high navigation accuracy through localized real-time analysis.
Solution Approach 2:
The system pre-generates and caches traffic index values for map tiles during off-peak periods. This preliminary action ensures that when real-time navigation queries occur, the system can quickly retrieve and update pre-computed data rather than performing complex calculations from scratch, thereby improving response time and reducing processing complexity.
2Reliability
If historical traffic pattern data is aggregated with current traffic data, then traffic prediction accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The system applies different processing qualities to different data elements: historical traffic patterns are aggregated at the map tile level rather than individual road segment level, while current real-time probe data is processed at the segment level. This local quality differentiation reduces overall computational burden while maintaining prediction accuracy where it matters most.
Solution Approach 2:
The system creates simplified copies of historical traffic data in the form of pre-computed traffic indices for each map tile. These copied representations allow rapid comparison with current conditions without requiring full re-processing of historical datasets, significantly reducing data processing time while preserving prediction reliability.
3Speed
If tile-based traffic index is generated and cached, then traffic information delivery speed is improved, but memory usage and storage requirements increase
Solution Approach 1:
Traffic information is segmented into discrete map tile units, each with its own cached traffic index. This segmentation allows the system to cache only the specific tiles that are currently relevant to active routes, rather than maintaining all possible traffic data in memory simultaneously, thus optimizing memory usage while maintaining fast delivery speed for active queries.
Solution Approach 2:
The system implements a caching strategy where less frequently accessed map tile data is discarded from fast memory and recovered from persistent storage only when needed. This approach maintains high delivery speed for commonly accessed tiles while reducing overall memory usage by allowing selective discarding and recovery of cached data based on current navigation demands.
Data Source
AI summary
The disclosure provides a method, a system, and a computer program product for predicting traffic information for at least one map tile area. The method comprises obtaining probe data and map attribute data for each of a plurality of road segments in the at least one map tile area. The method may include generating current traffic condition data for each of the plurality of road segments in the at least one map tile area based on the obtained probe data and the obtained map attribute data. The method may further include obtaining historical traffic pattern data associated with each of the plurality of road segments in the at least one map tile area. The method may further include generating a tile based traffic index (TTI) for the at least one map tile area based on aggregating the current traffic condition data and the historical traffic pattern data of the plurality of road segments in the at least one map tile area and providing TTI and predicting the traffic information for the at least one map tile area based on the generated tile based traffic index (TTI).