Indoor Likelihood Heatmap for Mobile Device Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing navigational and location-based services are inadequate for indoor environments, as outdoor positioning strategies using satellite signals are ineffective indoors, leading to challenges in accurately determining the location of mobile devices within complex indoor areas.
Innovation Solution
The generation and use of an indoor likelihood heatmap, which projects grid points over a schematic map of an indoor area, determines feasible paths and counts them to assign likelihood values to grid points, aiding in navigation and location estimation by indicating the probability of a mobile device's presence at specific points based on movement patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional signal measurement methods are used for indoor positioning, then positioning can be achieved, but energy consumption increases and computational complexity increases
Solution Approach 1:
The system pre-computes and stores likelihood heatmaps that indicate the probability of mobile devices being present at various locations based on movement patterns and obstructions. This preliminary computation allows the positioning system to query pre-processed data during actual positioning operations, significantly reducing real-time computational requirements and energy consumption while maintaining positioning accuracy.
Solution Approach 2:
Instead of performing complex real-time signal analysis, the system uses simplified likelihood heatmap representations that copy the essential positioning information in a compressed format. These heatmaps serve as probabilistic models that can be quickly queried to determine device location, reducing the computational burden compared to traditional signal measurement methods.
2Measurement precision
If traditional signal measurement methods are used for indoor positioning, then positioning can be achieved, but computational complexity increases
Solution Approach 1:
The system pre-computes and stores likelihood heatmaps that indicate the probability of mobile devices being present at various locations based on movement patterns and obstructions. This preliminary computation allows the positioning system to query pre-processed data during actual positioning operations, significantly reducing real-time computational requirements and energy consumption while maintaining positioning accuracy.
Solution Approach 2:
Instead of performing complex real-time signal analysis, the system uses simplified likelihood heatmap representations that copy the essential positioning information in a compressed format. These heatmaps serve as probabilistic models that can be quickly queried to determine device location, reducing the computational burden compared to traditional signal measurement methods.
3Adaptability or versatility
If outdoor positioning strategies are used indoors, then navigation services can be provided, but positioning becomes ineffective due to indoor obstructions
Solution Approach 1:
The system creates location-specific likelihood heatmaps that are tailored to the particular indoor environment, taking into account local obstructions, movement patterns, and spatial characteristics. Each heatmap provides localized probabilistic information about device presence that is specific to that indoor area, allowing navigation services to adapt to the unique constraints of indoor environments rather than relying on generic outdoor positioning strategies.
Solution Approach 2:
The system changes the fundamental parameters used for positioning from outdoor satellite-based signals to indoor movement pattern-based probabilities. By transforming the positioning approach from signal-strength dependent to pattern-recognition dependent, the system can effectively operate indoors where satellite signals are unavailable or unreliable, maintaining navigational service availability while improving positioning accuracy.
Data Source
AI summary
The subject matter disclosed herein may relate to methods, apparatuses, systems, devices or articles for generating or using an indoor likelihood heatmap, etc. For certain example implementations, a method for a device may comprise projecting multiple grid points over a schematic map of an indoor area, with the schematic map indicating multiple obstructions of the indoor area. Feasible paths between grid point pairs of the multiple grid points may be determined. For a particular grid point of the multiple grid points, a count of the feasible paths that traverse the particular grid point may be determined. A likelihood heatmap for use in one or more navigational applications may be generated based, at least in part, on the count. Other example implementations are described herein.


