Virtual Stop Line Mapping for Low-Data Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the vast amount of data they need to process and store, including visual information, GPS data, and sensor data, which can limit their navigation capabilities and require cumbersome traditional mapping technologies.
Innovation Solution
A system utilizing cameras to analyze images and process data for navigation, including detecting intersections, stopping locations, and other vehicles, with a processor that updates a road navigation model based on aggregated data from multiple vehicles, allowing for efficient data management and navigation without extensive mapping.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional mapping technology is used for autonomous vehicle navigation, then navigation accuracy can be maintained, but the volume of data needed to store and update the map becomes excessively large
Solution Approach 1:
The patent extracts only the essential navigation elements (stop lines, intersections, road geometry) from complete traditional maps. Instead of storing and processing entire map datasets, the system identifies and utilizes only the critical features needed for navigation decisions, dramatically reducing data volume while maintaining navigation reliability.
Solution Approach 2:
The patent segments the navigation problem into discrete detectable elements such as stop lines, intersections, and road segments. By breaking down continuous map data into segmented, identifiable features that can be detected by cameras and processors, the system reduces the complexity and volume of data required while preserving essential navigation information.
2Reliability
If vast volumes of visual information and sensor data are collected and processed, then navigation decisions can be made with complete information, but the processing complexity and computational burden increase significantly
Solution Approach 1:
The system extracts only the essential navigation-relevant information from vast volumes of sensor data and visual information. Instead of processing all collected data, the processor identifies and extracts critical elements such as stop lines, intersections, and relevant road features, reducing computational complexity while maintaining decision accuracy.
Solution Approach 2:
The patent implements preliminary action by pre-identifying and categorizing essential navigation features during the data collection phase. The system prepares and organizes only the necessary information elements before navigation decisions are required, reducing the complexity of real-time processing while ensuring complete information is available for decision-making.
3Loss of information
If complete traditional maps are stored and updated continuously, then up-to-date navigation information is available, but the storage requirements and update complexity become unmanageable
Solution Approach 1:
The patent extracts only the essential navigation features (stop lines, intersections, road geometry) from complete traditional maps for storage. Instead of storing entire map datasets, the system stores only the critical elements needed for navigation, dramatically reducing storage requirements while maintaining information currency through selective updates of these extracted features.
Data Source
AI summary
A navigation system may include a processor programmed to receive, from a camera of the host vehicle, one or more images captured from an environment of the host vehicle, and analyze the one or more images to detect an indicator of an intersection. The processor may also be programmed to determine, based on output received from at least one sensor of the host vehicle, a stopping location of the host vehicle relative to the detected intersection, and analyze the one or more images to determine an indicator of whether one or more other vehicles are in front of the host vehicle. The processor may further be programmed to send the stopping location of the host vehicle and the indicator of whether one or more other vehicles are in front of the host vehicle to a server for use in updating a road navigation model.