Vehicle Localization Mapping Using Predefined Static Object Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for localizing and mapping vehicles in environments, such as SLAM, face challenges in maintaining accuracy due to minor environmental changes like snowfall, growing grass, or falling leaves, which can result in localization errors.
Innovation Solution
A method that uses environment perception sensors to identify and filter measurements based on predefined patterns defined by static objects with specific shapes and offsets, allowing for more robust and reliable localization and mapping by disregarding slight environmental changes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If existing SLAM algorithms are used for localizing and mapping, then the method is efficient and accurate, but the accuracy deteriorates due to minor environmental changes like snowfall, growing grass, or falling leaves
Solution Approach 1:
The patent segments the environment into relevant features (objects matching predefined patterns) and irrelevant features (everything else). By filtering measurements to include only segmented objects that match the predefined pattern, the system achieves robust localization despite environmental changes. This segmentation approach allows the system to focus on stable, pattern-defined objects while ignoring transient environmental variations.
Solution Approach 2:
The patent applies local quality by assigning different importance weights to different parts of the environment. Objects matching the predefined pattern are given high importance for localization, while other environmental elements are excluded or given low importance. This selective weighting ensures that localization accuracy is maintained by relying on stable, pattern-defined features rather than the entire environment.
2Loss of information
If all measurement data is used for localization and mapping, then more information is available, but processing power requirements and computational complexity increase
Solution Approach 1:
The patent extracts only the essential information needed for localization by filtering measurements to include solely objects that match the predefined pattern. This extraction process removes irrelevant data from the measurement set, reducing the information volume that requires processing while maintaining the critical localization information. The filtered measurement set contains only pattern-matching objects, significantly reducing computational burden.
Solution Approach 2:
The patent applies partial action by using only a subset of available measurement data - specifically, only those measurements corresponding to objects matching the predefined pattern. This partial utilization of data is sufficient for accurate localization while avoiding the excessive processing requirements of using all available measurement data. The system processes less data but achieves the same or better localization performance.
3Measurement precision
If markers are placed in the environment for localization, then localization accuracy improves, but user accuracy in placing markers and system complexity increase
Solution Approach 1:
The patent implements self-service by enabling the system to automatically identify and select localization features from the environment without requiring manual marker placement. The predefined pattern acts as a template that the system uses to automatically detect suitable objects in the environment, eliminating the need for user intervention in marker placement. This automatic feature selection maintains high localization precision while greatly simplifying operation.
Solution Approach 2:
The patent applies preliminary action by pre-defining the pattern that localization features must match before actual localization occurs. This predefined pattern serves as a preparation step that guides the automatic identification process, allowing the system to quickly and accurately select appropriate features without requiring precise manual marker placement. The preliminary pattern definition replaces the need for user-accurate marker placement while maintaining high localization precision.
Data Source
AI summary
A method for localizing and/or mapping during operation of a vehicle an environment is provided. The vehicle comprises at least one environment perception sensor for the localizing and/or mapping. The method includes obtaining at least one measurement of the environment from the environment perception sensor, searching for and identifying a plurality of objects in the at least one measurement which correspond to a predefined pattern, in response to determining that the plurality of objects correspond to the predefined pattern, filtering the at least one measurement so that only the plurality of objects which correspond to the predefined pattern are used for the localizing and/or mapping, and localizing and/or mapping based on the filtered at least one measurement.