Vehicle Route Search Using Dynamic Tile ETA Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional route search methods using uniform cell division in road networks result in significant information loss, leading to inefficiencies and inaccuracies in calculating optimal routes due to varying link densities across regions.
Innovation Solution
A dynamic tile division method is applied in an ETA prediction model, where road networks are divided into tiles based on the number of links, using a quadrant tree expansion to minimize information loss and improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If the road network is divided into cells with the same size, then the division process is simple and uniform, but information loss in the road network increases due to varying link densities across regions
Solution Approach 1:
The patent divides the road network into multiple cells, but unlike conventional uniform division, each cell is dynamically sized based on the number of links it contains. This segmentation approach allows the system to handle varying link densities across different regions by creating cells with different sizes, thereby reducing information loss while maintaining a structured division framework.
Solution Approach 2:
The patent applies local quality by making each cell's size adaptive to its local characteristics (number of links). Cells in regions with high link density are divided into smaller units, while cells in low-density regions remain larger. This local adaptation ensures that each cell appropriately represents its regional characteristics, minimizing information loss without requiring uniform division throughout the entire network.
2Loss of information
If the road network is divided into cells with different sizes based on link number, then information loss is minimized, but the complexity of the division process increases
Solution Approach 1:
The patent implements a dynamic cell division process where cell sizes are not fixed beforehand but are determined based on the actual number of links in each region. This dynamic approach allows the system to adaptively create cells of varying sizes according to local link densities, reducing information loss while managing complexity through an automated, rule-based division algorithm rather than manual configuration.
3Productivity
If uniform cell division is used, then computation efficiency is maintained, but route search accuracy deteriorates due to information loss
Solution Approach 1:
The patent changes the key parameter of cell size from a fixed uniform value to a dynamic value determined by the number of links in each cell. This parameter change allows cells to adapt to local link densities, improving route search accuracy by better representing the road network structure. The computation efficiency is maintained through an automated algorithm that efficiently determines cell sizes based on link counts, rather than requiring complex manual configuration.
Data Source
AI summary
An apparatus for searching for an optimal route based on an entire route includes a Global Positioning System (GPS) module configured to detect a current position of a vehicle, a storage module configured to store digital map data, and a processor. The processor is configured to compute a plurality of candidate routes based on a route search engine on the basis of the current position and the digital map data. The processor is also configured to compute an optimal route by computing estimated time of arrivals (ETAs) of the plurality of candidate routes through an ETA prediction model.