Interpolated Lane Edge Fusion for Accurate Vehicle Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous and semi-autonomous vehicles face challenges in accurately identifying lane edges due to perspective distortions and noise in sensor and map data, which can lead to incorrect lane identification.
Innovation Solution
A system that interpolates and fuses sensor data and map data using a Kalman filter to generate predicted lane edge centers, allowing for accurate vehicle navigation by transmitting these centers to an autonomous controller.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If sensor data and map data are used directly for lane edge identification, then the processing is simple and fast, but the accuracy is reduced due to noise and perspective distortions
Solution Approach 1:
The patent applies preliminary interpolation to both sensor data and map data before fusion. The sensor data is interpolated to compensate for perspective distortions, and the map data is interpolated to match the sensor data's spatial resolution and coordinate system. This preliminary processing prepares the data for accurate fusion without requiring complex real-time calculations during navigation.
Solution Approach 2:
The patent introduces an interpolation process as an intermediary step between raw data acquisition and final lane edge identification. This intermediary process transforms the raw sensor and map data into a common reference frame with matched spatial characteristics, enabling accurate fusion while keeping the overall system complexity manageable.
2Measurement precision
If raw sensor data is used for lane edge detection, then the system is simple to operate, but the detection accuracy is low due to noise
Solution Approach 1:
The patent merges sensor data with map data through a fusion process. The interpolated sensor data and interpolated map data are combined to produce a more accurate lane edge identification than either data source could provide alone. This merging compensates for the noise in sensor data and the perspective distortions while maintaining operational simplicity.
3Reliability
If map data is used alone for lane identification, then the data is stable, but it lacks real-time accuracy due to noise and outdated information
Solution Approach 1:
The patent uses sensor data as feedback to update and refine the map data. The interpolated sensor data provides real-time measurements of lane edges that are fused with the interpolated map data. This feedback mechanism allows the system to maintain the stability of map data while incorporating real-time accuracy from sensor measurements.
Data Source
AI summary
A system that determines a nominal path based on interpolated lane edge data can include a processor and a memory. The memory includes instructions such that the processor is configured to receive a sensor data representing a perceived lane edge; receive map data including a lane edge; interpolate the sensor data and interpolate the map data; fuse the interpolated sensor data and the interpolated map data; and generate predicted lane edge lane edge centers based on the fused interpolated sensor data.