Lane-Mark Navigation Using Expected vs Actual Lateral Distance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating due to the sheer volume of data required for processing and storing information from various sources, such as cameras, GPS, and sensors, which can limit their navigation capabilities and pose daunting challenges in updating traditional mapping technologies.
Innovation Solution
The system employs cameras to analyze images and process data for autonomous vehicle navigation, using processors to detect lane marks, directional arrows, traffic lights, and free spaces, updating navigation models, and distributing them to other vehicles, enabling efficient navigation and decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional mapping technology is used to navigate, then navigation coverage is comprehensive, but the volume of data needed to store and update the map becomes excessively large
Solution Approach 1:
The patent segments the navigation system into multiple components: a server that stores comprehensive map data, vehicles that capture and transmit images, and a selective update mechanism that only transmits changed portions of the map. This segmentation allows comprehensive navigation coverage while reducing the data burden on individual vehicles.
Solution Approach 2:
The patent extracts only the necessary and changed portions of map data for transmission. Instead of transmitting entire maps or all sensor data, the system identifies and transmits only the specific road segments that have changed, significantly reducing data volume while maintaining navigation reliability.
2Reliability
If vast volumes of information are collected and analyzed, then navigation decisions are comprehensive, but processing time and computational burden increase
Solution Approach 1:
The system performs preliminary actions by pre-processing and storing comprehensive map data on the server before vehicles need it. The server pre-analyzes and organizes map information, so vehicles receive ready-to-use navigation data rather than processing raw information in real-time, reducing onboard processing time.
Solution Approach 2:
The patent introduces a server as an intermediary between map data sources and vehicles. The server handles the computationally intensive tasks of data aggregation, analysis, and processing, then provides processed results to vehicles. This intermediary approach maintains comprehensive navigation decision-making while reducing the computational burden and processing time at the vehicle level.
3Reliability
If frequent map updates are performed, then navigation accuracy is maintained, but the complexity and resource requirements of data management increase
Solution Approach 1:
The system implements a feedback mechanism where vehicles transmit captured images back to the server, which compares them with existing map data. The server automatically identifies changes and triggers updates only when necessary. This feedback loop maintains map accuracy while avoiding unnecessary updates and reducing data management complexity.
Solution Approach 2:
The patent changes the update parameter from time-based (frequent periodic updates) to event-based (updates triggered by detected changes). The system monitors for specific changes in road conditions, new constructions, or modifications, and updates the map only when such events occur. This approach maintains navigation accuracy while significantly reducing the frequency and complexity of updates.
Data Source
AI summary
A system for autonomously navigating a host vehicle along a road segment. The system includes at least one processor programmed to: receive from an image capture device at least one image representative of an environment of a host vehicle; determine a longitudinal position of the host vehicle along a target trajectory; determine an expected lateral distance to at least one lane mark based on the determined longitudinal position and based on two or more location identifiers associated with the at least one lane mark; analyze the at least one image to identify the at least one lane mark; determine an actual lateral distance to the at least one lane mark based on analysis of the at least one image; and determine an autonomous steering action for the host vehicle based on a difference between the expected lateral distance and the actual lateral distance.