Lane Marking Localization for Precise Vehicle Lateral Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current GPS technology is inaccurate for determining a vehicle's lateral position within a roadway, experiencing significant drift, which is unacceptable for advanced autonomous driving systems, and even when augmented with inertial measurement units, the precision remains insufficient for self-driving vehicles.
Innovation Solution
A system that approximates a vehicle's region using GPS or IMU devices, generates a response map from imaging device data, compares it to a region map from a database, and predicts the vehicle's location based on differences between response and region points, with the ability to output this information to advanced driver-assistance systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS technology is used to determine vehicle lateral position, then the system is simple and widely available, but the measurement precision is insufficient with drift of 1-10 meters
Solution Approach 1:
The patent combines GPS/IMU positioning data with visual lane marking detection data to create a hybrid positioning system. The GPS provides coarse location while visual systems provide fine lateral adjustment, merging two different measurement approaches to achieve both reasonable simplicity and high precision (10 cm or better).
Solution Approach 2:
The patent introduces an intermediary processing system that takes GPS coordinates and IMU data, combines them with visual lane marking information, and produces a refined lateral position estimate. This intermediary layer reconciles the coarse GPS data with precise visual measurements without requiring a complete system redesign.
2Measurement precision
If IMU is added to GPS to improve positioning accuracy, then the measurement precision improves somewhat, but the device complexity increases and drift remains too high for self-driving
Solution Approach 1:
The patent implements a feedback mechanism where the visual system continuously monitors lane marking positions and provides correction signals to adjust the GPS/IMU derived position. This feedback loop compensates for drift accumulation in the inertial system and maintains long-term accuracy without requiring more complex hardware.
Solution Approach 2:
The patent replaces reliance on purely mechanical/inertial measurement (IMU) with an optical/visual measurement system for lateral positioning. By using camera-based lane marking detection instead of depending on accelerometer and gyroscope integration, the system achieves better accuracy without proportionally increasing mechanical complexity.
3Measurement precision
If high-precision positioning system is implemented, then the measurement precision reaches 10 cm or less, but the device complexity and cost increase significantly
Solution Approach 1:
The patent makes the visual processing system serve multiple functions: lane detection for positioning, lane marking classification for road type identification, and potential speed estimation. This multi-functionality justifies the computational complexity by extracting maximum value from the same sensor and processing infrastructure.
Solution Approach 2:
The system uses the vehicle's existing camera infrastructure (already present for other ADAS functions) to perform lane marking detection and positioning. Rather than adding dedicated expensive sensors, the system makes the existing visual sensors serve the positioning function, reducing overall system complexity and cost.
Data Source
AI summary
Various embodiments of the present disclosure provide a system and method for lane marking localization that may be utilized by autonomous or semi-autonomous vehicles traveling within the lane. In the embodiment, the system comprises a locating device adapted to determine the vehicle's geographic location; a database; a region map; a response map; a camera; and a computer connected to the locating device, database, and camera, 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 form 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 generate a predicted vehicle location based on the comparison of the response map and region map.