Lane Route Mapping From Fleet Orientation Histograms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining lane routes in vehicle navigation rely solely on geometric infrastructure or fleet driving behavior, which are inadequate for complete coverage and accuracy, especially in unstructured areas with missing lane markings.
Innovation Solution
A method using a central computing unit to process geometric map data and fleet data, applying a grid with specified cells, determining vehicle orientations, generating histograms, and employing a learning-based approach to derive lane routes, incorporating both geometric and driving behavior data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lane routes are determined solely based on geometric infrastructure, then geometric accuracy is improved, but coverage in unstructured areas deteriorates
Solution Approach 1:
The patent combines geometric infrastructure data with fleet driving behavior data to determine lane routes. The system processes both geometric map data (from infrastructure) and fleet data (from vehicle positions and orientations) through a learning-based method, merging these two data sources to achieve both geometric accuracy and coverage in unstructured areas where infrastructure data may be missing or incomplete.
2Adaptability or versatility
If lane routes are determined solely based on fleet driving behavior, then coverage in unstructured areas is improved, but geometric accuracy deteriorates
Solution Approach 1:
The system merges fleet driving behavior data with geometric infrastructure data. The learning-based method processes both types of data together, using geometric data to ensure accuracy where infrastructure is present and using fleet behavior data to fill gaps in unstructured areas, thereby achieving both coverage and accuracy simultaneously.
3Measurement precision
If manual reworking is used for geometric infrastructure, then accuracy is improved, but automation level deteriorates
Solution Approach 1:
The system performs self-service through automated processing. The central computing unit automatically processes geometric map data and fleet data using a learning-based method to determine lane routes. The system self-corrects and refines lane route determinations by analyzing patterns in fleet driving behavior data, eliminating the need for manual reworking while maintaining high accuracy.
4Extent of automation
If fully automated lane route determination is implemented, then automation level is improved, but accuracy in complex scenarios deteriorates
Solution Approach 1:
The system uses feedback from fleet driving behavior data to continuously improve automated lane route determination. The learning-based method analyzes actual vehicle positions and orientations from the fleet, using this feedback to refine and correct automated lane route determinations, thereby maintaining high accuracy in complex scenarios while preserving full automation.
Data Source
AI summary
A central computing unit determines and provides lane routes of streets to vehicles of a vehicle fleet. A geometric map having geometric lane boundaries and applying a grid with grid cells of a specified size to the map is provided. Fleet data is collected from fleet, the fleet data including position sequences covered by the fleet vehicles. Vehicle orientations of the vehicles at positions of the grid cells are determined from the collected position sequences. The determined vehicle orientations are discretized and a histogram is generated for each individual grid cell position for the discretized vehicle orientations. A map section having a specified amount of grid cells is selected and the lane routes on the map section are determined using a learning-based method from the histograms created for the grid cells of the map section and the geometric lane boundaries on the map section.