Wheel-Based Vehicle Positioning for Shape-Independent Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional vehicle positioning systems face challenges in accurately detecting the position and direction of vehicles with non-dominant features or changing shapes, particularly during manufacturing, as they require detection methods specific to different vehicle shapes.
Innovation Solution
A vehicle positioning apparatus that uses wheel information acquisition units to gather data from wheel detectors, enabling the estimation of vehicle position and direction using wheel positions, tire angles, and reference data, allowing for common detection methods across various vehicle shapes and specifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the entire shape of the vehicle is used for position detection, then the detection method can capture vehicle-specific features, but it requires different detection methods for different vehicle shapes and manufacturing stages
Solution Approach 1:
The patent segments the vehicle into multiple wheels as discrete detection targets. Instead of detecting the entire vehicle shape, the system divides the detection task into identifying individual wheel positions, which are then used to calculate vehicle position and orientation. This segmentation allows the same detection method to work across different vehicle shapes and manufacturing stages.
Solution Approach 2:
The patent extracts the wheels as key feature elements from the vehicle body for detection purposes. By focusing specifically on wheel positions rather than the complex entire vehicle shape, the system achieves reliable detection that is independent of vehicle body variations, manufacturing changes, or missing features.
2Measurement precision
If multiple wheels are detected to improve position accuracy, then the vehicle position estimation becomes more accurate, but the processing cost and complexity increase
Solution Approach 1:
The patent creates a universal detection system that can handle any number of wheels (2, 3, or 4 wheels) using the same algorithmic framework. The position estimation unit is designed to process wheel combinations flexibly, determining vehicle position based on available wheel detections without requiring complex differentials for each wheel configuration.
Solution Approach 2:
The patent uses reference data that represents the positional relationships between wheels and vehicle coordinates. By copying and applying these reference relationships to detected wheel positions, the system efficiently estimates vehicle position without complex real-time calculations, reducing processing complexity while maintaining accuracy.
3Measurement precision
If wheel information from multiple wheels is used, then the position and direction estimation becomes more accurate, but the data processing requirements and computational cost increase
Solution Approach 1:
The patent pre-establishes reference data containing the positional relationships between wheels and vehicle coordinate systems. This preliminary preparation allows the system to quickly estimate vehicle position and direction by matching detected wheel positions against these pre-computed references, avoiding complex real-time geometric calculations and reducing computational power requirements.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A vehicle positioning apparatus comprises a wheel information acquisition unit configured to acquire wheel information from a wheel detector that measures the wheel information, the wheel information being at least either an image of at least one wheel of a plurality of wheels provided with a vehicle capable of running by unmanned driving or three-dimensional point cloud data about the at least one wheel. The vehicle positioning apparatus comprises a wheel position acquisition unit configured to acquire the position of the at least one wheel using the acquired wheel information; and a position estimation unit configured to estimate the position and direction of the vehicle using the acquired position of the at least one wheel.