Vehicle Lane Estimation Using Map Data Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle position estimation devices face accuracy issues in estimating the traveling lane, especially when the accuracy based on vehicle parameters is poor, and errors in in-lane position estimation occur.
Innovation Solution
A vehicle position estimation device that calculates the reliability of each lane based on external information and map data, independent of the vehicle's in-lane position, allowing for accurate lane estimation even with poor initial accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If lane estimation is based on vehicle parameters (in-lane position), then the estimation process is simple, but the accuracy deteriorates when vehicle parameter accuracy is poor
Solution Approach 1:
The patent introduces map data as an intermediary element that bridges the gap between satellite positioning and lane estimation. The map data includes pre-stored lane information that serves as a reference framework, allowing the system to infer lane position indirectly through spatial relationships between the vehicle and mapped road features, thereby improving accuracy without requiring direct measurement of in-lane position
Solution Approach 2:
The patent transitions from one-dimensional vehicle parameter measurement (in-lane position) to a multi-dimensional estimation approach by incorporating satellite positioning (latitude/longitude), map data (road network topology), and external information (surrounding objects). This dimensional expansion allows the system to resolve lane estimation ambiguity through spatial reasoning across multiple reference frames
2Reliability
If lane estimation relies on in-lane position data, then the system can operate with simple sensors, but errors occur when in-lane position estimation is inaccurate
Solution Approach 1:
The patent performs preliminary actions by pre-storing accurate lane information in map data before the vehicle reaches those locations. This pre-acquired lane data serves as a reference that can be compared against current sensor measurements, allowing the system to detect and correct deviations from expected lane positions before they propagate into significant estimation errors
Solution Approach 2:
The system implements feedback by continuously comparing current lane estimation results with map data and external information. When discrepancies are detected between estimated lane position and expected position from map data, the system adjusts its estimation, creating a closed-loop correction mechanism that reduces the impact of sensor errors
3Measurement precision
If the system uses multiple data sources (external information, vehicle parameters, satellite positioning, map data), then lane estimation accuracy improves, but device complexity increases
Solution Approach 1:
The patent segments the data processing task into distinct functional modules: external information acquisition unit, vehicle parameter acquisition unit, satellite positioning acquisition unit, map data acquisition unit, and position estimation unit. Each module processes specific types of data independently, and the results are combined in a systematic manner, making the complex multi-source integration manageable through modular architecture
Data Source
AI summary
A vehicle position estimation device includes an external information acquisition unit for acquiring external information, a vehicle parameter acquisition unit for acquiring a vehicle parameter, a satellite positioning acquisition unit for acquiring a latitude and longitude of a self-position of the vehicle, a map data acquisition unit for acquiring map data, and a position estimation unit. The position estimation unit estimates the self-position, and includes a reliability calculation unit and a lane estimation unit. The reliability calculation unit calculates a reliability of each lane based on the external information and the map data when the vehicle is traveling on a road having multiple lanes. The reliability of each lane indicates a probability of the vehicle being traveling in the lane among the lanes. The lane estimation unit estimates a lane in which the vehicle is located by using the reliability calculated by the reliability calculation unit.