Multi-Map Vehicle Alignment Using Relative Object Positions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated vehicles face challenges in aligning map data from multiple sources, which are often collected in different reference frames, leading to potential misalignment relative to world GPS coordinates, and existing methods may not adequately address rotational differences or errors in object positioning.
Innovation Solution
A navigation system that uses on-board sensors and perception sensors to determine the location of a host-vehicle on multiple digital maps by correlating relative positions of objects, such as lane markers, and aligns maps only when coordinates differ by less than an error threshold, using a controller to adjust for errors and rotational differences by identifying additional objects for alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If map data from multiple sources is collected in different reference frames and aligned using a single object, then the alignment procedure can be simplified, but the measurement precision deteriorates due to inadequate handling of rotational differences and positioning errors
Solution Approach 1:
The patent transitions from using a single localization object to using multiple localization objects (at least two objects) for alignment. This adds a dimensional aspect to the alignment process by incorporating multiple reference points, which enables the system to account for rotational differences and positioning errors that cannot be detected with a single object. The multiple objects provide additional constraints that resolve the trade-off between procedural simplicity and alignment precision.
Solution Approach 2:
The system implements a verification mechanism where it checks whether the aligned maps correctly position the vehicle relative to a second perceived object (such as a lane marker) within an error threshold (e.g., 20 cm). This feedback loop allows the system to reject alignment instances that fail to meet precision requirements and retry with different object combinations, thereby maintaining high measurement precision while managing the complexity through iterative refinement.
2Measurement precision
If the system uses multiple objects for alignment verification, then the measurement precision improves, but the device complexity increases due to additional sensors and processing requirements
Solution Approach 1:
The patent employs perception sensors that serve multiple functions: they detect localization objects (such as street signs) for coordinate determination, detect secondary objects (such as lane markers) for verification, and provide relative position information for both alignment and error checking. This multi-functionality reduces the need for separate dedicated sensors for each task, thereby limiting the increase in device complexity while maintaining high measurement precision through multiple object verification.
3Reliability
If the system rejects alignment instances outside error threshold, then the reliability improves, but the loss of time increases due to repeated alignment attempts
Solution Approach 1:
The system performs preliminary rough positioning using GPS or other coarse localization methods before attempting precise alignment with multiple objects. This preliminary action establishes an initial coordinate framework that guides the subsequent fine-tuning process, reducing the number of iterative attempts needed to achieve alignment within the error threshold. By preparing the initial position estimate in advance, the system minimizes time loss while maintaining high reliability through the subsequent verification steps.
Data Source
Figure 1
Figure 2
AI summary
A navigation system (10) for an automated vehicle includes an object-detector (18), a first-map (24), a second-map (30), and a controller (36). The object-detector (18) indicates relative-positions (20) of a plurality of objects (22) proximate to the host-vehicle (12). The first-map (24) indicates a first-object (26) and a second-object (28) detected by the object-detector (18). The second-map (30) is different from the first-map (24). The second-map (30) indicates the first-object (26) and the second-object (28). The controller (36) is in communication with the object-detector (18), the first-map (24), and the second-map (30). The controller (36) is configured to determine a first-coordinate (40) of the host-vehicle (12) on the first-map (24) based on the relative-positions (20) of the first-object (26) and the second-object (28), determine a second-coordinate (50) of the host-vehicle (12) on the second-map (30) based on the relative-positions (20) of the first-object (26) and the second-object (28), and align the first-map (24) and the second-map (30) based on the first-coordinate (40), the second-coordinate (50), and the relative-positions (20) of the first-object (26) and the second-object (28).