Floor Plan Structural Analysis for Accessible Building Navigation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for capturing and utilizing building interior information, such as floor plans, are inefficient and difficult to scale, maintain, and do not effectively provide navigational data for users, especially for users with mobility limitations.

Innovation Solution

Utilizing computing devices to automatically determine structural characteristics and attributes from building floor plans and images, without depth sensors, to generate navigational data, including accessibility, connectivity, and visibility information, using machine learning and image analysis to create adjacency graphs and vector embeddings.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional floor plan methods are used to capture building interior information, then some layout information can be obtained, but the methods are difficult to construct, maintain, and scale efficiently

Engineering Contradiction:

Improveefficiency of capturing building informationVSAvoiddifficulty to construct and maintain floor plans

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent replaces manual floor plan construction and analysis with automated computer vision and machine learning systems. Image capture devices automatically capture building interiors, and AI algorithms process these images to extract structural characteristics, eliminating the need for manual floor plan creation and analysis while significantly improving efficiency and scalability

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates digital representations (copies) of building interiors through image capture and processing. Instead of physically measuring and drawing floor plans, the system captures visual copies of the building interior and uses these images as the basis for automated analysis, enabling efficient replication and scaling across multiple buildings

Inventive Principle:

Principle #26Copying

2Loss of information

If floor plans are manually populated with room interior information, then detailed building data can be obtained, but the process is time-consuming and difficult to maintain

Engineering Contradiction:

Improvecompleteness of building interior informationVSAvoidtime to capture and populate floor plan data

Core Design Contradiction:

Loss of informationVSLoss of time

Solution Approach 1:

The patent performs preliminary automated processing of building images to extract structural characteristics before navigation queries are made. The system pre-processes images to identify walls, doors, windows, and room layouts, storing this extracted information for rapid retrieval during navigation, eliminating the need for time-consuming manual data population at query time

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces manual information gathering with automated image analysis. Computer vision algorithms automatically extract building interior information from captured images, identifying structural elements and spatial relationships without human intervention, thereby obtaining complete information while minimizing time investment

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If comprehensive building analysis is performed to provide navigational data, then accurate navigation information can be provided, but computing power and time requirements increase

Engineering Contradiction:

Improveaccuracy of navigational dataVSAvoidcomputing power required for building analysis

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The patent divides the building analysis into distinct segments: image capture, structural characteristic extraction, adjacency graph generation, and navigation query processing. Each segment is handled independently and efficiently, allowing the system to process only relevant portions of building data for each navigation query, reducing overall computing requirements while maintaining accuracy

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary extraction of structural characteristics from building images and generates adjacency graphs in advance. This pre-processing creates optimized data structures that enable rapid navigation queries without requiring intensive computing power at query time, balancing accuracy with computational efficiency

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12548218B2Automated building information determinations from floor plan structural analysis

Publication Date: 2026.02.10 MFTB HOLDCO INC

AI summary

Techniques are described for using computing devices to perform automated operations for determining matching buildings and using corresponding information in further automated manners, such as by determining buildings having similarities to an indicated target building based at least in part on building floor plans and/or other attributes, and by automatically determining building modifications to implement for the target building based at least in part on differences with the similar buildings and/or building features that are prioritized or deprioritized from analysis of user activity data of one or more types, optionally in combination with one or more other specified criteria. Information about such determined buildings may be used in various automated manners, including for controlling device navigation (e.g., autonomous vehicles), for display on client devices in corresponding graphical user interfaces, for further analysis to identify shared and/or aggregate characteristics, etc.