Lane Marking Fusion for Precise Vehicle Lateral Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current GPS technology for autonomous vehicles is inaccurate, leading to significant lateral position drift, which is unacceptable for self-driving applications, even when augmented with inertial measurement units, as it fails to achieve the required precision of 10 cm or less.
Innovation Solution
A system and method that combines GPS and IMU data with environmental imaging from multiple cameras to create response maps, comparing them to regional maps stored in a database to accurately determine a vehicle's lateral position within a roadway lane, using a processor to fuse data and generate a confidence score for precise localization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS technology is used to determine vehicle lateral position, then positioning function is provided, but measurement precision deteriorates with drift of 10 meters or more
Solution Approach 1:
The patent combines GPS positioning data with visual recognition data from cameras and map data from databases to create a fused positioning result. The system merges multiple independent positioning methods to achieve higher precision than any single method alone, resolving the contradiction between providing positioning function and maintaining measurement precision.
Solution Approach 2:
The system continuously compares the vehicle's predicted position with actual visual recognition of lane markers and environmental features, using the difference as feedback to correct positioning drift. This closed-loop feedback mechanism maintains long-term positioning stability and precision by constantly adjusting for accumulated errors.
2Measurement precision
If multiple imaging devices and data fusion are used to improve positioning precision, then measurement precision improves to 10 cm or less, but device complexity increases
Solution Approach 1:
The system uses general-purpose cameras and processors that can perform multiple functions: capturing images for visual recognition, processing GPS data, comparing with map data, and fusing results. This multi-functionality reduces the need for specialized components, achieving high precision positioning while controlling device complexity.
Solution Approach 2:
The system uses the vehicle's existing infrastructure (cameras already installed for other purposes, onboard processors, existing GPS receivers) to perform positioning tasks. By making existing components serve multiple purposes including high-precision positioning, the system achieves 10 cm accuracy without adding significant complexity.
Data Source
AI summary
Various embodiments provide a system and method for iterative lane marking localization that may be utilized by autonomous or semi-autonomous vehicles traveling within the lane. In an embodiment, the system comprises a locating device adapted to determine the vehicle's geographic location; a database; a region map; a response map; a plurality of cameras; and a computer connected to the locating device, database, and cameras, wherein the computer is adapted to receive the region map, wherein the region map corresponds to a specified geographic location; generate the response map by receiving information from the camera, the information relating to the environment in which the vehicle is located; identifying lane markers observed by the camera; and plotting identified lane markers on the response map; compare the response map to the region map; and iteratively generate a predicted vehicle location based on the comparison of the response map and the region map.