Lane Course Mapping Using Fleet Orientation Histograms
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining lane layouts in road infrastructure are either incomplete without manual rework or do not achieve full coverage based solely on geometric infrastructure or fleet driving behavior.
Innovation Solution
A method using a central computer unit that combines geometric infrastructure and fleet driving behavior, employing a learning-based approach to derive lane paths by generating histograms from vehicle orientations within grid cells, allowing for scalable and accurate lane modeling, including unstructured areas and changes in infrastructure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If route guidance data is provided for the entire route in advance, then the driver receives comprehensive navigation information, but the driver cannot adequately respond to actual driving conditions that arise during the journey
Solution Approach 1:
The patent divides the route guidance into segments: advance route information (turn-by-turn instructions) and real-time event information (actual driving conditions). The system provides comprehensive navigation data in advance while separately capturing and transmitting actual driving conditions during the journey, allowing the driver to respond appropriately to real-time situations while having complete navigation guidance.
Solution Approach 2:
The system performs preliminary action by providing complete route guidance data before the driver begins the journey, including all turn-by-turn instructions and route information. This allows the driver to plan ahead while the system subsequently captures actual driving conditions to enable real-time responses, resolving the contradiction between advance information provision and adaptive response capability.
2Adaptability or versatility
If the system waits to determine actual driving conditions before providing guidance, then the information is highly relevant to current conditions, but the driver experiences delays in receiving necessary navigation information
Solution Approach 1:
The system provides route guidance information in advance based on the planned route, without waiting to determine actual driving conditions. Turn-by-turn instructions and navigation data are delivered before the driver needs them, eliminating delays while the system simultaneously captures actual driving conditions for real-time adaptability.
Solution Approach 2:
The patent separates route guidance information delivery from actual driving condition determination. Navigation instructions are provided in advance based on the route plan, while actual driving conditions are captured separately during the journey. This segmentation allows timely information delivery without waiting for real-time condition analysis.
3Loss of information
If detailed route guidance is provided for the entire route, then the driver has complete navigation information, but the driver may become overwhelmed and lose the ability to independently evaluate actual driving conditions
Solution Approach 1:
The patent segments information presentation into advance route guidance (turn-by-turn instructions) and real-time actual driving condition feedback. By providing comprehensive navigation information in a structured, segmented format rather than as a continuous stream, the driver can process information more effectively while maintaining the ability to independently evaluate actual driving conditions as they arise.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The invention relates to a method for determining and providing lane courses for roads by means of a central computer unit coupled for data transmission to vehicles of a vehicle fleet. According to the invention, the method comprises the following steps: providing a geometric map (K) with geometric lane boundaries (S) and applying a grid (G) with grid cells (G1 to G49) of a predefined size to the map (K); collecting fleet data for vehicles of the vehicle fleet, wherein the fleet data comprises position sequences travelled by the vehicles of the vehicle fleet; determining vehicle orientations of the vehicles in positions of the grid cells (G1 to G49) from the collected position sequences; discretising the determined vehicle orientations; for individual grid cell positions, determining a respective histogram (H) for the discretised vehicle orientations determined in the position of the respective grid cell (G1 to G49); selecting a map section with a predefined number of grid cells (G1 to G49); and determining the lane courses on the map section by means of a learning-based method from the histogram (H) created for the grid cells (G1 to G49) of the map section and the geometric lane boundaries (S) on the map section.