Lane Curvature Determination Using Interpolated Coordinate Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for determining lane curvature in autonomous vehicles are limited by look-ahead distance and environmental conditions for vision-based systems, and existing map data often provides curvature for entire roadways rather than specific lanes.
Innovation Solution
A system that uses a computer with a processor and memory to receive sample coordinate points, generate interpolated points, fit a curve, and output lane curvature, allowing for accurate curvature determination over a greater distance and specific lane, using piecewise cubic Hermite interpolation polynomials and calculating mean curvatures to improve accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If vision-based techniques are used to determine lane curvature, then the system can recognize lane markers in real-time, but the look-ahead distance is limited and accuracy deteriorates in environmental conditions like rain or fog
Solution Approach 1:
The patent introduces map data as an intermediary information source to supplement vision-based lane curvature detection. By combining real-time camera data with pre-stored high-precision map data, the system achieves more reliable curvature determination in environmental conditions where vision alone is insufficient
Solution Approach 2:
The patent merges two different data sources - vision-based real-time detection and map-based curvature data - into a unified lane curvature determination system. This combination allows the system to leverage the strengths of both methods while compensating for their individual weaknesses
2Area of stationary object
If map data is used to determine lane curvature, then curvature information is available for the entire roadway, but the data provides curvature for the entire roadway rather than specific lanes
Solution Approach 1:
The patent applies local quality by filtering and selecting only the curvature data relevant to the specific lane the vehicle is traveling in, rather than using curvature data for the entire roadway. This is achieved by matching the vehicle's current lane position with corresponding lane-specific curvature information from the map data
Solution Approach 2:
The patent segments the roadway curvature data into individual lane-specific curvature data. By dividing the overall roadway curvature information into separate lane components, the system can provide accurate curvature data for the specific lane while maintaining coverage of the entire roadway
3Measurement precision
If interpolated coordinate points are generated and curve fitting is applied, then lane curvature accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary actions by pre-generating interpolated coordinate points and pre-fitting curves to the map data during map data preparation. This allows the system to store pre-computed curvature information that can be quickly retrieved and applied during real-time operation, reducing on-board computational complexity
Data Source
AI summary
A computer includes a processor and a memory storing instructions executable by the processor to receive a series of sample coordinate points of a projected path of travel of a vehicle, generate interpolated coordinate points along the projected path between the sample coordinate points, fit a curve to the sample coordinate points and interpolated coordinate points, and output a curvature of a lane at a reported coordinate point along the projected path based on the curve.