Lane Index Estimation From Image Data for AV Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing localization methods for autonomous vehicles, relying on GNSS and inertial measurement units, are computationally expensive or inaccurate in areas with reduced signal reception, leading to errors in location and resolution.
Innovation Solution
Utilizing machine learning models trained on historical image data to generate lane offset and index information based on real-time image data from sensors, such as cameras and LiDAR, to improve localization accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If GNSS and IMU are used for localization, then location information can be obtained, but computational expense increases and accuracy deteriorates in areas with reduced signal reception
Solution Approach 1:
The patent replaces the traditional GNSS/IMU localization system with a vision-based machine learning system. Instead of relying on satellite signals and inertial sensors, the system uses image data from cameras processed through trained machine learning models to determine lane offset and vehicle position, thereby avoiding computational expenses and signal reception issues associated with traditional methods
Solution Approach 2:
The patent introduces machine learning models as an intermediary between raw image data and localization output. The trained models process visual features and extract lane offset information, serving as a mediator that translates image data into accurate position information without requiring direct GNSS/IMU signal processing
2Measurement precision
If GNSS and IMU are used for localization, then location data can be obtained, but location resolution deteriorates in areas with reduced signal reception
Solution Approach 1:
The patent substitutes the signal-dependent GNSS/IMU system with a vision-based system that is immune to signal reception conditions. By using camera images and machine learning to determine lane offset and vehicle position, the system achieves consistent location resolution regardless of satellite signal availability
Solution Approach 2:
The patent creates a virtual representation of the vehicle's position relative to lane markings by processing image data through machine learning models. This virtual copy of position information, derived from visual features rather than satellite signals, maintains high resolution in signal-deprived environments
Data Source
AI summary
Systems and methods for training and executing machine learning models to generate lane index values are disclosed. A method includes identifying a set of image data captured by at least one autonomous vehicle when the at least autonomous vehicle is positioned in a lane of a roadway and respective ground truth localization data; determining a plurality of lane index values for the set of image data based on the ground truth localization data; labeling the set of image data with the plurality of lane index values, the lane index values representing a number of lanes from a leftmost or rightmost lane to the lane in which the at least one autonomous vehicle was positioned; and training, using the labeled set of image data, a plurality of machine learning models that generate a left lane index value and a right lane index value as output.