Surface Scan Feature Matching for Robust Robot Localization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing localization methods for mobile robots face challenges such as difficulty in responding to changing environments, dependence on signal strength, vulnerability to reference transmitter failures, and high computational demands for mapping and updating.

Innovation Solution

An apparatus and method that utilize a processing unit to extract extraction information from scanning data of a surface, determine descriptors for inherent features, and match these with a database to determine the position of a detection unit, thereby enabling robust and efficient localization.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If marker-based localization methods are used, then localization accuracy is improved, but device complexity and ease of operation deteriorate due to requiring manual marker placement and maintenance

Engineering Contradiction:

Improvelocalization accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system uses naturally occurring speckled patterns on the ground surface as localization markers, eliminating the need for manual marker placement and maintenance. The ground surface itself provides the localization features through its inherent speckling, making the system self-configuring and reducing operational complexity

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces expensive, manually placed physical markers with inexpensive, naturally occurring speckled patterns on the ground. These natural features require no installation cost and are permanently available, effectively replacing costly marker infrastructure

Inventive Principle:

Principle #27Cheap short-living objects (Disposable)

2Adaptability or versatility

If SLAM algorithms are used for mapping and localization, then adaptability to changing environments is improved, but computational load and processing time increase

Engineering Contradiction:

Improveenvironmental adaptabilityVSAvoidcomputational load

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The system extracts only the essential localization features (speckled patterns) from the environment rather than performing full SLAM mapping of the entire scene. By focusing extraction on specific ground surface patterns, it achieves localization without the heavy computational burden of complete environmental mapping

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs partial localization by using only ground surface speckles for position determination, rather than comprehensive SLAM processing of all environmental features. This partial approach provides sufficient localization accuracy with reduced computational requirements

Inventive Principle:

Principle #16Partial or excessive action

3Ease of operation

If radio-based localization methods are used, then localization capability is improved, but reliability deteriorates due to signal strength dependency and transmitter failures

Engineering Contradiction:

Improvelocalization capabilityVSAvoidsystem reliability

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system replaces radio-based electronic localization with optical image processing of ground surface patterns. By substituting radio wave dependency with visual pattern recognition, it eliminates signal strength issues, interference problems, and transmitter failure vulnerabilities associated with radio-based methods

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Productivity

If high-speed localization is implemented, then productivity is improved, but measurement precision may deteriorate due to reduced processing time

Engineering Contradiction:

Improvelocalization speedVSAvoidposition accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The system segments the localization process into efficient stages: capturing ground surface images, extracting speckle patterns, comparing with pre-stored reference patterns, and determining position. This segmentation enables fast processing while maintaining accuracy through focused feature extraction rather than exhaustive analysis

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12293595B2Extraction of extraction information from scanning information of a surface for use with a database

Publication Date: 2025.05.06 FRAUNHOFER GESELLSCHAFT ZUR FORDERUNG DER ANGEWANDTEN FORSCHUNG EV

AI summary

An apparatus having a processing unit configured to obtain scanning information, provided by a detection unit, from a scan of a surface, wherein the scanning information have information on an inherent feature of the surface. Furthermore, the processing unit is configured to extract extraction information for the inherent feature from the scanning information and to perform matching with a database based on the extraction information, wherein extraction information for a plurality of inherent features of the surface are stored in the database. Furthermore, the processing unit is configured to determine the position of the detection unit based on the matching.