Road Mark Recognition for Vehicle Positioning Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing driver assistance systems face inaccuracies in vehicle positioning, particularly along straight sections of roads, due to limitations in GPS and odometer errors, which affect the precision of navigation and lane detection.
Innovation Solution
A method and apparatus that identify and learn the absolute location of distinctive road marks and distances between them in real-time, using sensors like cameras, acceleration sensors, and inertial sensors, to augment navigation systems and improve positional accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS-based positioning is used for vehicle navigation, then the system can provide basic location information, but the positioning accuracy deteriorates with errors of 10 meters or more
Solution Approach 1:
The patent introduces road marks as intermediary reference objects between the GPS system and the vehicle positioning system. These road marks serve as mediators that provide high-precision reference points for correcting GPS positioning errors, enabling the system to achieve centimeter-level accuracy instead of meter-level accuracy.
Solution Approach 2:
The patent replaces reliance on purely satellite-based mechanical positioning (GPS) with a hybrid system that incorporates optical recognition of road marks. By substituting the mechanical GPS positioning method with optical-mechanical recognition of fixed road infrastructure, the system achieves significantly higher positioning precision.
2Productivity
If odometer-based distance measurement is used for tracking vehicle position along the road, then the system can calculate distance traveled, but the error accumulates continuously at a rate of at least 0.2% of driven distance
Solution Approach 1:
The patent implements a feedback mechanism where the vehicle's position is continuously corrected by comparing the recognized road mark positions with the odometer-based calculated position. This feedback loop prevents error accumulation by periodically resetting the positioning reference to the high-precision road mark locations.
Solution Approach 2:
The system performs preliminary positioning correction by identifying road marks before the accumulated odometer error becomes significant. By proactively using road marks as reference points, the system prevents large error accumulation rather than correcting it after the fact.
Data Source
AI summary
A technique for assisting driving a vehicle and for learning at least one distance between first and second distinctive marks on or at a road is disclosed. In method aspects, a first method comprises the steps of identifying the first distinctive mark on or at a road on which the vehicle is travelling, retrieving, from a database, a distance between the first distinctive mark and the second distinctive mark, calculating, based on a location of the vehicle relative to the first distinctive mark, the relative distance of the vehicle to the second distinctive mark taking into account the distance between the first and second distinctive marks, and assisting the driving of the vehicle based on the calculated relative distance. A second method comprises the steps of identifying the first and second distinctive marks, calculating the distance between the first and second distinctive marks, and storing the distance between the first and second distinctive marks.